{"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/2309-05973","title":"Circuit Breaking: Removing Model Behaviors with Targeted Ablation","arxiv_id":"2309.05973","date":"2023-09-12","proceeding":null,"authors":["Maximilian Li","Xander Davies","Max Nadeau"],"abstract":"Language models often exhibit behaviors that improve performance on a pre-training objective but harm performance on downstream tasks. We propose a novel approach to removing undesirable behaviors by ablating a small number of causal pathways between model components, with the intention of disabling the computational circuit responsible for the bad behavior. Given a small dataset of inputs where the model behaves poorly, we learn to ablate a small number of important causal pathways. In the setting of reducing GPT-2 toxic language generation, we find ablating just 12 of the 11.6K causal edges mitigates toxic generation with minimal degradation of performance on other inputs.","url_abs":"https://arxiv.org/abs/2309.05973v2","url_pdf":"https://arxiv.org/pdf/2309.05973v2.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":"2309-05973","repo_url":"https://github.com/xanderdavies/circuit-breaking","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-2","method_name":"GPT-2"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2309.05973","atlas_url":"https://app.syntology.ai/?focus=2309.05973","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05973"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2309.05973"},"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":"2309.05973"},"call":"get_harvested_code_for_paper(arxiv_id=\"2309.05973\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2309.05973"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2309.05973\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2309.05973"},"call":"get_concepts_for_paper(arxiv_id=\"2309.05973\")"}],"by_repo":[{"repo":"xanderdavies/circuit-breaking","kind":"official","samples":12,"ran":9,"instrument":0,"unverified":3}],"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","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/2309.05973.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/2309.05973.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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/xanderdavies/circuit-breaking","reach":{"status":"ok"}}],"summary":{"ran":9,"unverified":3},"n_samples":12,"n_ran":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":3,"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":12,"ran":9,"n_ran_checked":9,"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":12,"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":9,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","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":"bb8e7ced3c0abfa9","code_sha256_prefix":"bb8e7ced3c0abfa9","entry":"filter_text","repo":"xanderdavies/circuit-breaking","repo_kind":"official","path":"toxicity/data_preprocessing.py","file_url":"https://github.com/xanderdavies/circuit-breaking/blob/HEAD/toxicity/data_preprocessing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"text:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","retrieve_with":{"tool":"get_code","code_sha256":"bb8e7ced3c0abfa9"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xanderdavies/circuit-breaking when it was checked","mcp_get_code":{"code_sha256":"bb8e7ced3c0abfa9"}},{"code_sha256":"c889aff403e3ccae","code_sha256_prefix":"c889aff403e3ccae","entry":"get_data","repo":"xanderdavies/circuit-breaking","repo_kind":"official","path":"toxicity/data_preprocessing.py","file_url":"https://github.com/xanderdavies/circuit-breaking/blob/HEAD/toxicity/data_preprocessing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"toxicity_scores:list/1/tuple, num_samples:int/0/int, toxicity_range:list/1/int, num_test_samples:int/0/int, num_buckets:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/get-data","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xanderdavies/circuit-breaking when it was checked","mcp_get_code":{"code_sha256":"c889aff403e3ccae"}},{"code_sha256":"ba9b47ba89029051","code_sha256_prefix":"ba9b47ba89029051","entry":"get_mnist_3s_w_bad","repo":"xanderdavies/circuit-breaking","repo_kind":"official","path":"mnist/data.py","file_url":"https://github.com/xanderdavies/circuit-breaking/blob/HEAD/mnist/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"train_dataset_grouped:TensorDataset/0/?, train_dataset:TensorDataset/0/?, test_dataset_grouped:TensorDataset/0/?, test_dataset:TensorDataset/0/?, bad_behaviors:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xanderdavies/circuit-breaking when it was checked","mcp_get_code":{"code_sha256":"ba9b47ba89029051"}},{"code_sha256":"4785260563d2c44a","code_sha256_prefix":"4785260563d2c44a","entry":"group_mnist","repo":"xanderdavies/circuit-breaking","repo_kind":"official","path":"mnist/data.py","file_url":"https://github.com/xanderdavies/circuit-breaking/blob/HEAD/mnist/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"train_dataset:TensorDataset/0/?, test_dataset:TensorDataset/0/?, seed:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xanderdavies/circuit-breaking when it was checked","mcp_get_code":{"code_sha256":"4785260563d2c44a"}},{"code_sha256":"e14402ea7d99d023","code_sha256_prefix":"e14402ea7d99d023","entry":"l05_regularization","repo":"xanderdavies/circuit-breaking","repo_kind":"official","path":"mnist/mlp_model.py","file_url":"https://github.com/xanderdavies/circuit-breaking/blob/HEAD/mnist/mlp_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?, l05_lambda:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xanderdavies/circuit-breaking when it was checked","mcp_get_code":{"code_sha256":"e14402ea7d99d023"}},{"code_sha256":"7a90d9617759fa76","code_sha256_prefix":"7a90d9617759fa76","entry":"l1_regularization","repo":"xanderdavies/circuit-breaking","repo_kind":"official","path":"mnist/mlp_model.py","file_url":"https://github.com/xanderdavies/circuit-breaking/blob/HEAD/mnist/mlp_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?, l1_lambda:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":"/code/l1-regularization","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xanderdavies/circuit-breaking when it was checked","mcp_get_code":{"code_sha256":"7a90d9617759fa76"}},{"code_sha256":"9f61bbbd76ea7d8a","code_sha256_prefix":"9f61bbbd76ea7d8a","entry":"prepare_fixed_demo","repo":"xanderdavies/circuit-breaking","repo_kind":"official","path":"toxicity/inference.py","file_url":"https://github.com/xanderdavies/circuit-breaking/blob/HEAD/toxicity/inference.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"tokenizer:callable/0/?, batch_size:int/0/int, demo:str/0/str, device:str/0/str","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xanderdavies/circuit-breaking when it was checked","mcp_get_code":{"code_sha256":"9f61bbbd76ea7d8a"}},{"code_sha256":"c5ccb3834251f5f3","code_sha256_prefix":"c5ccb3834251f5f3","entry":"retrieve_toxic_filtered_data","repo":"xanderdavies/circuit-breaking","repo_kind":"official","path":"toxicity/data.py","file_url":"https://github.com/xanderdavies/circuit-breaking/blob/HEAD/toxicity/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"batch_size:int/0/int, split:str/0/str","fixture_out_type":"DataLoader","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xanderdavies/circuit-breaking when it was checked","mcp_get_code":{"code_sha256":"c5ccb3834251f5f3"}},{"code_sha256":"a2a7bd73e9052bbd","code_sha256_prefix":"a2a7bd73e9052bbd","entry":"tokenize_and_concatenate_list","repo":"xanderdavies/circuit-breaking","repo_kind":"official","path":"toxicity/data.py","file_url":"https://github.com/xanderdavies/circuit-breaking/blob/HEAD/toxicity/data.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"text_samples:list/1/str, tokenizer:callable/0/?, seq_len:int/0/int","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T15:16:18.137819+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xanderdavies/circuit-breaking when it was checked","mcp_get_code":{"code_sha256":"a2a7bd73e9052bbd"}},{"code_sha256":"5cefb8a41654c608","code_sha256_prefix":"5cefb8a41654c608","entry":"epoch","repo":"xanderdavies/circuit-breaking","repo_kind":"official","path":"mnist/train_eval.py","file_url":"https://github.com/xanderdavies/circuit-breaking/blob/HEAD/mnist/train_eval.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/epoch","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xanderdavies/circuit-breaking when it was checked","mcp_get_code":{"code_sha256":"5cefb8a41654c608"}},{"code_sha256":"8fbf87f49043e30f","code_sha256_prefix":"8fbf87f49043e30f","entry":"infer_batch_with_owt","repo":"xanderdavies/circuit-breaking","repo_kind":"official","path":"toxicity/inference.py","file_url":"https://github.com/xanderdavies/circuit-breaking/blob/HEAD/toxicity/inference.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":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xanderdavies/circuit-breaking when it was checked","mcp_get_code":{"code_sha256":"8fbf87f49043e30f"}},{"code_sha256":"306013836f145d62","code_sha256_prefix":"306013836f145d62","entry":"retrieve_toxic_data_low_loss","repo":"xanderdavies/circuit-breaking","repo_kind":"official","path":"toxicity/data.py","file_url":"https://github.com/xanderdavies/circuit-breaking/blob/HEAD/toxicity/data.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":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, xanderdavies/circuit-breaking when it was checked","mcp_get_code":{"code_sha256":"306013836f145d62"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"87a2e41f5af2160434f660bfdeb446b9eb343bc7894d9111fa67a85531a0f697","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}