{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/locating-and-editing-factual-knowledge-in-gpt","title":"Locating and Editing Factual Associations in GPT","arxiv_id":"2202.05262","date":"2022-02-10","proceeding":null,"authors":["Kevin Meng","David Bau","Alex Andonian","Yonatan Belinkov"],"abstract":"We analyze the storage and recall of factual associations in autoregressive transformer language models, finding evidence that these associations correspond to localized, directly-editable computations. We first develop a causal intervention for identifying neuron activations that are decisive in a model's factual predictions. This reveals a distinct set of steps in middle-layer feed-forward modules that mediate factual predictions while processing subject tokens. To test our hypothesis that these computations correspond to factual association recall, we modify feed-forward weights to update specific factual associations using Rank-One Model Editing (ROME). We find that ROME is effective on a standard zero-shot relation extraction (zsRE) model-editing task, comparable to existing methods. To perform a more sensitive evaluation, we also evaluate ROME on a new dataset of counterfactual assertions, on which it simultaneously maintains both specificity and generalization, whereas other methods sacrifice one or another. Our results confirm an important role for mid-layer feed-forward modules in storing factual associations and suggest that direct manipulation of computational mechanisms may be a feasible approach for model editing. The code, dataset, visualizations, and an interactive demo notebook are available at https://rome.baulab.info/","url_abs":"https://arxiv.org/abs/2202.05262v5","url_pdf":"https://arxiv.org/pdf/2202.05262v5.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"locating-and-editing-factual-knowledge-in-gpt","repo_url":"https://github.com/kmeng01/rome","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"locating-and-editing-factual-knowledge-in-gpt","repo_url":"https://github.com/hiyouga/fastedit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"locating-and-editing-factual-knowledge-in-gpt","repo_url":"https://github.com/keltin13/concept-rot","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"locating-and-editing-factual-knowledge-in-gpt","repo_url":"https://gitee.com/zhengkeli/zkl-knowedit-rome","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"model-editing","task_name":"Model Editing"},{"task_slug":"relation-extraction","task_name":"Relation Extraction"},{"task_slug":"specificity","task_name":"Specificity"},{"task_slug":null,"task_name":"counterfactual"}],"methods":[{"method_slug":"rome","method_name":"ROME"}],"datasets_introduced":[],"methods_introduced":[{"slug":"rome","name":"ROME","full_name":"Rank-One Model Editing"}],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2202.05262","atlas_url":"https://app.syntology.ai/?focus=2202.05262","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.05262"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2202.05262"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2202.05262"},"call":"get_harvested_code_for_paper(arxiv_id=\"2202.05262\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2202.05262"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2202.05262\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2202.05262"},"call":"get_concepts_for_paper(arxiv_id=\"2202.05262\")"}],"by_repo":[{"repo":"kmeng01/rome","kind":"official","samples":1,"ran":1,"instrument":1,"unverified":0},{"repo":"hiyouga/fastedit","kind":"listed","samples":12,"ran":2,"instrument":1,"unverified":10},{"repo":"keltin13/concept-rot","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2412.13341"],"harvested_for_calls":[{"arxiv_id":"2412.13341","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2412.13341"},"call":"get_harvested_code_for_paper(arxiv_id=\"2412.13341\")"}]},{"repo":"gitee.com/zhengkeli/zkl-knowedit-rome","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"EleutherAI/knowledge-neurons","kind":"found_in_text","samples":2,"ran":1,"instrument":0,"unverified":1}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","assemblies":[{"assembly_sha256":"23f7a1f2db06bd30","source_kind":"harvested","method_name":"Rank-One Model Editing (ROME)","realizes_method":"Rank-One Model Editing (ROME)","graph_method":"Rank-One Model Editing (ROME)","realizes_severed":false,"claim":"This code implements Rank-One Model Editing (ROME), a method to locate and edit factual associations in transformer language models by updating specific weight matrices in a single layer.","centrality":"contribution","entry":"apply_rome_to_model","entry_sha256":"38ac32a8532239ff","n_bricks":13,"bricks":[{"entry":"apply_rome_to_model","code_sha256":"38ac32a8532239ff","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"ROMEHyperParams","code_sha256":"337cf805ba7488b9","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"execute_rome","code_sha256":"20e375abcab5cc8a","role":"update_rule","order":2,"level":0,"status":"unverified"},{"entry":"upd_matrix_match_shape","code_sha256":"3a7359734df0b9a0","role":"helper","order":3,"level":2,"status":"ran_fixture"},{"entry":"HyperParams","code_sha256":"b93905c630cab5f8","role":"helper","order":4,"level":0,"status":"unverified"},{"entry":"compute_u","code_sha256":"2ab22a551cc021f7","role":"helper","order":5,"level":0,"status":"unverified"},{"entry":"compute_v","code_sha256":"39f6e26e03a21b1e","role":"helper","order":6,"level":0,"status":"unverified"},{"entry":"get_inv_cov","code_sha256":"196e16a6fd176c0b","role":"helper","order":7,"level":0,"status":"unverified"},{"entry":"get_reprs_at_idxs","code_sha256":"7c626c3970ff2baf","role":"helper","order":8,"level":0,"status":"unverified"},{"entry":"get_reprs_at_word_tokens","code_sha256":"96bd9a8c0145d685","role":"helper","order":9,"level":0,"status":"unverified"},{"entry":"find_fact_lookup_idx","code_sha256":"be38085054387516","role":"helper","order":10,"level":1,"status":"ran_fixture"},{"entry":"get_module_input_output_at_word","code_sha256":"98f3e85c4a9f9bb3","role":"helper","order":11,"level":0,"status":"unverified"},{"entry":"get_words_idxs_in_templates","code_sha256":"612d15cebbf71774","role":"helper","order":12,"level":0,"status":"unverified"}],"ran_individually":3,"ran_individually_constructed":1,"ran_individually_by_status":{"ran":1,"ran_fixture":2},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4ed3c9c4c1bb","n_siblings":1,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"},{"assembly_sha256":"fe474871597f1162","source_kind":"harvested","method_name":"Rank-One Model Editing (ROME)","realizes_method":"Rank-One Model Editing (ROME)","graph_method":"Rank-One Model Editing (ROME)","realizes_severed":false,"claim":"The code implements a method to edit factual associations in transformer models by patching intermediate activations in feed-forward layers, corresponding to the Rank-One Model Editing (ROME) approach.","centrality":"contribution","entry":"patch_ff_layer","entry_sha256":"9412d866514a01ef","n_bricks":4,"bricks":[{"entry":"patch_ff_layer","code_sha256":"9412d866514a01ef","role":"entry","order":0,"level":0,"status":"unverified"},{"entry":"Patch","code_sha256":"a79ceec9a50ca78f","role":"helper","order":1,"level":1,"status":"ran"},{"entry":"get_attributes","code_sha256":"44b3ed63235aa487","role":"helper","order":2,"level":1,"status":"ran_draft_wrong"},{"entry":"set_attribute_recursive","code_sha256":"5a801e530acadf2c","role":"helper","order":3,"level":0,"status":"unverified"}],"ran_individually":2,"ran_individually_constructed":0,"ran_individually_by_status":{"ran":1,"ran_draft_wrong":1},"end_to_end":{"ran":false,"level":0},"level_lowered":null,"claim_match":"IMPLEMENTS","claim_match_rule":"single_judge","claim_match_basis":"judge:global.anthropic.claude-sonnet-4-5-20250929-v1:0","claim_match_judges":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"label_verdict":"matches","label_verdict_judged":true,"suggested_method":null,"batch_at":"2026-09-09T22:44:46+00:00","sibling_group":"4ed3c9c4c1bb","n_siblings":1,"retention":"keep","provenance":"assembly:harvest_method_v6","attached_at":"2026-09-09T22:44:46+00:00","attached_provenance":"assembly:harvest_method_v6"}],"assembly_sibling_groups":[{"group":"4ed3c9c4c1bb","realizes_method":"Rank-One Model Editing (ROME)","source_kind":"harvested","batch_at":"2026-09-09T22:44:46+00:00","members":["23f7a1f2db06bd30","fe474871597f1162"]}],"assemblies_is":{"about":"What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results.","harvested":"assembled from code harvested from a repository linked to the paper","generated":"generated from the paper text, not the repository's code","end_to_end":"for a harvested assembly, the assembly has not been run end-to-end; for a generated one, end_to_end.level is the assembly's own level and against_independent_peer says whether it ran against a peer: an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists","bricks_level":"each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level","ran_individually":"a COUNT of bricks that ran on their own on a fixture (split by status in ran_individually_by_status), not a level; instrument statuses are failures of Syntology's instrument, not of the code","siblings":"assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another","judged":"Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as \"by construction\" or \"not judged by a model\"","level_lowered":"a generated assembly whose level Syntology's graph lowered, with the level it had, the recorded reason and when","retention":"Syntology's spending triage for further verification, not a verdict","claim_match":"the claim_match vote: IMPLEMENTS, COMPONENT or UNCLEAR. Where claim_match_basis is \"judge:<model>\", it is one model's judgement of the assembly's label against the paper's claim (claim_match_rule single_judge, the model in claim_match_judges): not a verification and not a run. Where it is \"construction\", the value was set when the code was generated for this method and no model judged it, whatever claim_match_rule says. The page prints no claim match for any assembly","label_verdict":"whether the assembly's code is the method it is labelled with: matches, cannot_tell, mislabelled (suggested_method names what it looks like instead) or not_the_method; label_verdict_judged is true only when a model read the code (claim_match_basis \"judge:<model>\")","label_verdict_judged":"where true (claim_match_basis \"judge:<model>\"), label_verdict is a single model's judgement; not calibrated; not printed on the page; where false, it was set by construction, and the page prints it unless the node is shared with another paper (node_properties_written_for)","claim":"the claim text stored on the assembly node: for a harvested assembly, what the paper claims the code implements, as the lifting model wrote it; for a generated one, the specification the code was generated from. Not verified text","centrality":"how central the lifted method is to the paper, as the lifting step recorded it: contribution, component or incidental","v3_tests_passed_both_sides":"end_to_end.v3_tests_passed_both_sides: the number of property tests derived from the paper that passed on both implementations, as the attached report lists them; a level 3 card with 0 says its report lists none","ran_individually_constructed":"ran_individually_constructed: of the bricks counted in ran_individually, how many constructed an object rather than computing a result (Syntology's RAN record's rule, read from the graph-layer sample with the brick's code_sha256); a part of ran_individually, never subtracted from it and never a failure; null where a brick that ran has no sample in the graph layer this build read, so the figure was not counted"},"assemblies_call":{"tool":"assembly","arguments":{"arxiv_id":"2202.05262"},"call":"assembly(arxiv_id=\"2202.05262\")"},"read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2202.05262.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2202.05262.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/EleutherAI/knowledge-neurons","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kmeng01/rome","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/keltin13/concept-rot","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://gitee.com/zhengkeli/zkl-knowedit-rome","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hiyouga/fastedit","reach":null}],"summary":{"ran_fixture":2,"ran":2,"unverified":11},"n_samples":15,"n_ran":4,"n_constructed":1,"n_ran_checked":2,"n_instrument":2,"n_unverified":11,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":1,"ran":1,"n_ran_checked":0,"n_instrument":1,"repositories":1},"listed":{"samples":12,"ran":2,"n_ran_checked":1,"n_instrument":1,"repositories":1},"found_in_text":{"samples":2,"ran":1,"n_ran_checked":1,"n_instrument":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":3,"n_ran_without_level_date":1,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"3a7359734df0b9a0","code_sha256_prefix":"3a7359734df0b9a0","entry":"upd_matrix_match_shape","repo":"kmeng01/rome","repo_kind":"official","path":"rome/rome_main.py","file_url":"https://github.com/kmeng01/rome/blob/HEAD/rome/rome_main.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":2,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"signature":"matrix:Tensor/2/float, shape:Size/1/int","fixture_out_type":"Tensor","code_page":"/code/upd-matrix-match-shape","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3a7359734df0b9a0"}},{"code_sha256":"a79ceec9a50ca78f","code_sha256_prefix":"a79ceec9a50ca78f","entry":"Patch","repo":"EleutherAI/knowledge-neurons","repo_kind":"found_in_text","path":"knowledge_neurons/patch.py","file_url":"https://github.com/EleutherAI/knowledge-neurons/blob/HEAD/knowledge_neurons/patch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"x:Tensor/3/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"a79ceec9a50ca78f"},"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"a79ceec9a50ca78f"}},{"code_sha256":"337cf805ba7488b9","code_sha256_prefix":"337cf805ba7488b9","entry":"ROMEHyperParams","repo":"hiyouga/fastedit","repo_kind":"listed","path":"fastedit/rome/rome_main.py","file_url":"https://github.com/hiyouga/fastedit/blob/HEAD/fastedit/rome/rome_main.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"fixture_out_type":"ROMEHyperParams","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"337cf805ba7488b9"}},{"code_sha256":"be38085054387516","code_sha256_prefix":"be38085054387516","entry":"find_fact_lookup_idx","repo":"hiyouga/fastedit","repo_kind":"listed","path":"fastedit/rome/rome_main.py","file_url":"https://github.com/hiyouga/fastedit/blob/HEAD/fastedit/rome/rome_main.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"prompt:str/0/str, subject:str/0/str, tokenizer:callable/0/?, fact_token_strategy:str/0/str, verbose:bool/0/bool","fixture_out_type":"int","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"be38085054387516"}},{"code_sha256":"b93905c630cab5f8","code_sha256_prefix":"b93905c630cab5f8","entry":"HyperParams","repo":"hiyouga/fastedit","repo_kind":"listed","path":"fastedit/rome/rome_main.py","file_url":"https://github.com/hiyouga/fastedit/blob/HEAD/fastedit/rome/rome_main.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/hyperparams","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b93905c630cab5f8"}},{"code_sha256":"38ac32a8532239ff","code_sha256_prefix":"38ac32a8532239ff","entry":"apply_rome_to_model","repo":"hiyouga/fastedit","repo_kind":"listed","path":"fastedit/rome/rome_main.py","file_url":"https://github.com/hiyouga/fastedit/blob/HEAD/fastedit/rome/rome_main.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"38ac32a8532239ff"}},{"code_sha256":"2ab22a551cc021f7","code_sha256_prefix":"2ab22a551cc021f7","entry":"compute_u","repo":"hiyouga/fastedit","repo_kind":"listed","path":"fastedit/rome/rome_main.py","file_url":"https://github.com/hiyouga/fastedit/blob/HEAD/fastedit/rome/rome_main.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2ab22a551cc021f7"}},{"code_sha256":"39f6e26e03a21b1e","code_sha256_prefix":"39f6e26e03a21b1e","entry":"compute_v","repo":"hiyouga/fastedit","repo_kind":"listed","path":"fastedit/rome/rome_main.py","file_url":"https://github.com/hiyouga/fastedit/blob/HEAD/fastedit/rome/rome_main.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"39f6e26e03a21b1e"}},{"code_sha256":"20e375abcab5cc8a","code_sha256_prefix":"20e375abcab5cc8a","entry":"execute_rome","repo":"hiyouga/fastedit","repo_kind":"listed","path":"fastedit/rome/rome_main.py","file_url":"https://github.com/hiyouga/fastedit/blob/HEAD/fastedit/rome/rome_main.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"20e375abcab5cc8a"}},{"code_sha256":"196e16a6fd176c0b","code_sha256_prefix":"196e16a6fd176c0b","entry":"get_inv_cov","repo":"hiyouga/fastedit","repo_kind":"listed","path":"fastedit/rome/rome_main.py","file_url":"https://github.com/hiyouga/fastedit/blob/HEAD/fastedit/rome/rome_main.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-inv-cov","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"196e16a6fd176c0b"}},{"code_sha256":"98f3e85c4a9f9bb3","code_sha256_prefix":"98f3e85c4a9f9bb3","entry":"get_module_input_output_at_word","repo":"hiyouga/fastedit","repo_kind":"listed","path":"fastedit/rome/rome_main.py","file_url":"https://github.com/hiyouga/fastedit/blob/HEAD/fastedit/rome/rome_main.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"98f3e85c4a9f9bb3"}},{"code_sha256":"7c626c3970ff2baf","code_sha256_prefix":"7c626c3970ff2baf","entry":"get_reprs_at_idxs","repo":"hiyouga/fastedit","repo_kind":"listed","path":"fastedit/rome/rome_main.py","file_url":"https://github.com/hiyouga/fastedit/blob/HEAD/fastedit/rome/rome_main.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7c626c3970ff2baf"}},{"code_sha256":"96bd9a8c0145d685","code_sha256_prefix":"96bd9a8c0145d685","entry":"get_reprs_at_word_tokens","repo":"hiyouga/fastedit","repo_kind":"listed","path":"fastedit/rome/rome_main.py","file_url":"https://github.com/hiyouga/fastedit/blob/HEAD/fastedit/rome/rome_main.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"96bd9a8c0145d685"}},{"code_sha256":"612d15cebbf71774","code_sha256_prefix":"612d15cebbf71774","entry":"get_words_idxs_in_templates","repo":"hiyouga/fastedit","repo_kind":"listed","path":"fastedit/rome/rome_main.py","file_url":"https://github.com/hiyouga/fastedit/blob/HEAD/fastedit/rome/rome_main.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/get-words-idxs-in-templates","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"612d15cebbf71774"}},{"code_sha256":"9412d866514a01ef","code_sha256_prefix":"9412d866514a01ef","entry":"patch_ff_layer","repo":"EleutherAI/knowledge-neurons","repo_kind":"found_in_text","path":"knowledge_neurons/patch.py","file_url":"https://github.com/EleutherAI/knowledge-neurons/blob/HEAD/knowledge_neurons/patch.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"9412d866514a01ef"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ba099a898a9e7d0f1b2729e86264b4db9efa23f3145d87d16c3f7907a0d24b33","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}