{"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/sparse-autoencoders-reveal-selective","title":"Sparse autoencoders reveal selective remapping of visual concepts during adaptation","arxiv_id":"2412.05276","date":"2024-12-06","proceeding":null,"authors":["Hyesu Lim","Jinho Choi","Jaegul Choo","Steffen Schneider"],"abstract":"Adapting foundation models for specific purposes has become a standard approach to build machine learning systems for downstream applications. Yet, it is an open question which mechanisms take place during adaptation. Here we develop a new Sparse Autoencoder (SAE) for the CLIP vision transformer, named PatchSAE, to extract interpretable concepts at granular levels (e.g. shape, color, or semantics of an object) and their patch-wise spatial attributions. We explore how these concepts influence the model output in downstream image classification tasks and investigate how recent state-of-the-art prompt-based adaptation techniques change the association of model inputs to these concepts. While activations of concepts slightly change between adapted and non-adapted models, we find that the majority of gains on common adaptation tasks can be explained with the existing concepts already present in the non-adapted foundation model. This work provides a concrete framework to train and use SAEs for Vision Transformers and provides insights into explaining adaptation mechanisms.","url_abs":"https://arxiv.org/abs/2412.05276v1","url_pdf":"https://arxiv.org/pdf/2412.05276v1.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":"sparse-autoencoders-reveal-selective","repo_url":"https://github.com/dynamical-inference/patchsae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"sparse-autoencoder","method_name":"Sparse Autoencoder"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2412.05276","atlas_url":"https://app.syntology.ai/?focus=2412.05276","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.05276"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2412.05276"},"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":"2412.05276"},"call":"get_harvested_code_for_paper(arxiv_id=\"2412.05276\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2412.05276"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2412.05276\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2412.05276"},"call":"get_concepts_for_paper(arxiv_id=\"2412.05276\")"}],"by_repo":[{"repo":"dynamical-inference/patchsae","kind":"official","samples":6,"ran":5,"instrument":3,"unverified":1}],"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/2412.05276.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/2412.05276.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/dynamical-inference/patchsae","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"ran_draft_wrong":3,"unverified":1},"n_samples":6,"n_ran":5,"n_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":1,"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":6,"ran":5,"n_ran_checked":2,"n_instrument":3,"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":5,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-25","last":"2026-09-25","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":"c0113839c1642005","code_sha256_prefix":"c0113839c1642005","entry":"calculate_entropy","repo":"dynamical-inference/patchsae","repo_kind":"official","path":"analysis/utils.py","file_url":"https://github.com/dynamical-inference/patchsae/blob/HEAD/analysis/utils.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"top_val:Tensor/2/float, top_label:Tensor/2/int, ignore_label_idx:NoneType/0/?, eps:float/0/float","fixture_out_type":"Tensor","level_recorded_at":"2026-09-25T04:30:57.282821+00:00","code_page":"/code/calculate-entropy","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c0113839c1642005"}},{"code_sha256":"8b00d270f0a5a818","code_sha256_prefix":"8b00d270f0a5a818","entry":"get_predictions","repo":"dynamical-inference/patchsae","repo_kind":"official","path":"tasks/classification_with_top_k_masking.py","file_url":"https://github.com/dynamical-inference/patchsae/blob/HEAD/tasks/classification_with_top_k_masking.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"vit:callable/0/?, inputs:dict/0/?, text_features:Tensor/2/float, vit_type:str/0/str, hooks:NoneType/0/?","fixture_out_type":"list","level_recorded_at":"2026-09-25T15:42:09.353852+00:00","code_page":"/code/get-predictions","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8b00d270f0a5a818"}},{"code_sha256":"4a7cb61e02537776","code_sha256_prefix":"4a7cb61e02537776","entry":"get_scheduler","repo":"dynamical-inference/patchsae","repo_kind":"official","path":"src/sae_training/utils.py","file_url":"https://github.com/dynamical-inference/patchsae/blob/HEAD/src/sae_training/utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"scheduler_name:str/0/str, optimizer:SGD/0/?, warm_up_steps:int/0/int, training_steps:int/0/int, lr_end:float/0/float, num_cycles:int/0/int","fixture_out_type":"LambdaLR","level_recorded_at":"2026-09-25T04:30:57.282821+00:00","code_page":"/code/get-scheduler","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"4a7cb61e02537776"}},{"code_sha256":"b251e3420ace47d7","code_sha256_prefix":"b251e3420ace47d7","entry":"load_checkpoint","repo":"dynamical-inference/patchsae","repo_kind":"official","path":"src/models/utils.py","file_url":"https://github.com/dynamical-inference/patchsae/blob/HEAD/src/models/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"fpath:str/0/str","fixture_out_type":"dict","level_recorded_at":"2026-09-25T15:42:09.353852+00:00","code_page":"/code/load-checkpoint","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b251e3420ace47d7"}},{"code_sha256":"effece23664132b2","code_sha256_prefix":"effece23664132b2","entry":"load_state_dict_without_prompt_learner","repo":"dynamical-inference/patchsae","repo_kind":"official","path":"src/models/utils.py","file_url":"https://github.com/dynamical-inference/patchsae/blob/HEAD/src/models/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"ckpt_path:str/0/str","fixture_out_type":"dict","level_recorded_at":"2026-09-25T15:42:09.353852+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"effece23664132b2"}},{"code_sha256":"daa2ff5af7df15ac","code_sha256_prefix":"daa2ff5af7df15ac","entry":"load_stats","repo":"dynamical-inference/patchsae","repo_kind":"official","path":"analysis/utils.py","file_url":"https://github.com/dynamical-inference/patchsae/blob/HEAD/analysis/utils.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/load-stats","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"daa2ff5af7df15ac"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"11cee31f46268e4266608d6dafdfffbb31761e04947efb24ad209fb33aa31bed","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}