{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/optimal-ablation-for-interpretability","title":"Optimal ablation for interpretability","arxiv_id":"2409.09951","date":"2024-09-16","proceeding":null,"authors":["Maximilian Li","Lucas Janson"],"abstract":"Interpretability studies often involve tracing the flow of information through machine learning models to identify specific model components that perform relevant computations for tasks of interest. Prior work quantifies the importance of a model component on a particular task by measuring the impact of performing ablation on that component, or simulating model inference with the component disabled. We propose a new method, optimal ablation (OA), and show that OA-based component importance has theoretical and empirical advantages over measuring importance via other ablation methods. We also show that OA-based component importance can benefit several downstream interpretability tasks, including circuit discovery, localization of factual recall, and latent prediction.","url_abs":"https://arxiv.org/abs/2409.09951v1","url_pdf":"https://arxiv.org/pdf/2409.09951v1.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":"optimal-ablation-for-interpretability","repo_url":"https://github.com/maxtli/optimalablation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.09951","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.09951"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","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/maxtli/optimalablation","reach":null}],"summary":{"ran_fixture":2,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"ran":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":3,"samples":[{"code_sha256_prefix":"bc7e2c07f328c883","entry":"a_inner_prod","repo":"maxtli/optimalablation","repo_kind":"official","path":"utils/lens_utils.py","file_url":"https://github.com/maxtli/optimalablation/blob/HEAD/utils/lens_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bc7e2c07f328c883"}},{"code_sha256_prefix":"eea2ba282a7a5d83","entry":"a_sim","repo":"maxtli/optimalablation","repo_kind":"official","path":"utils/lens_utils.py","file_url":"https://github.com/maxtli/optimalablation/blob/HEAD/utils/lens_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eea2ba282a7a5d83"}},{"code_sha256_prefix":"ed504ae4d0e6f8e2","entry":"compile_loss_dfs","repo":"maxtli/optimalablation","repo_kind":"official","path":"utils/lens_utils.py","file_url":"https://github.com/maxtli/optimalablation/blob/HEAD/utils/lens_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ed504ae4d0e6f8e2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}