{"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/attribution-patching-outperforms-automated","title":"Attribution Patching Outperforms Automated Circuit Discovery","arxiv_id":"2310.10348","date":"2023-10-16","proceeding":null,"authors":["Aaquib Syed","Can Rager","Arthur Conmy"],"abstract":"Automated interpretability research has recently attracted attention as a potential research direction that could scale explanations of neural network behavior to large models. Existing automated circuit discovery work applies activation patching to identify subnetworks responsible for solving specific tasks (circuits). In this work, we show that a simple method based on attribution patching outperforms all existing methods while requiring just two forward passes and a backward pass. We apply a linear approximation to activation patching to estimate the importance of each edge in the computational subgraph. Using this approximation, we prune the least important edges of the network. We survey the performance and limitations of this method, finding that averaged over all tasks our method has greater AUC from circuit recovery than other methods.","url_abs":"https://arxiv.org/abs/2310.10348v2","url_pdf":"https://arxiv.org/pdf/2310.10348v2.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":"attribution-patching-outperforms-automated","repo_url":"https://github.com/aaquib111/acdcpp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":{"status":"ok"}},{"paper_slug":"attribution-patching-outperforms-automated","repo_url":"https://github.com/FlyingPumba/circuits-benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"attribution-patching-outperforms-automated","repo_url":"https://github.com/flyingpumba/interpbench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"attribution-patching-outperforms-automated","repo_url":"https://github.com/hannamw/eap-ig","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"attribution-patching-outperforms-automated","repo_url":"https://github.com/technion-cs-nlp/peap","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2310.10348","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.10348"}},"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/FlyingPumba/circuits-benchmark","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hannamw/eap-ig","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/flyingpumba/interpbench","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/aaquib111/acdcpp","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/technion-cs-nlp/peap","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"1e69174684fa3e06","entry":"gen_flipped_prompts","repo":"aaquib111/acdcpp","repo_kind":"official","path":"ioi_task/ioi_dataset.py","file_url":"https://github.com/aaquib111/acdcpp/blob/HEAD/ioi_task/ioi_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1e69174684fa3e06"}},{"code_sha256_prefix":"77cc485677cb046a","entry":"gen_prompt_uniform","repo":"aaquib111/acdcpp","repo_kind":"official","path":"ioi_task/ioi_dataset.py","file_url":"https://github.com/aaquib111/acdcpp/blob/HEAD/ioi_task/ioi_dataset.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"77cc485677cb046a"}},{"code_sha256_prefix":"4891a91f0e41a7ca","entry":"generate_random_color","repo":"aaquib111/acdcpp","repo_kind":"official","path":"utils/graphics_utils.py","file_url":"https://github.com/aaquib111/acdcpp/blob/HEAD/utils/graphics_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4891a91f0e41a7ca"}},{"code_sha256_prefix":"f131b48a560c7101","entry":"pareto_optimal_sublist","repo":"aaquib111/acdcpp","repo_kind":"official","path":"greaterthan_task/minimal_acdc_node_roc.py","file_url":"https://github.com/aaquib111/acdcpp/blob/HEAD/greaterthan_task/minimal_acdc_node_roc.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f131b48a560c7101"}},{"code_sha256_prefix":"c8154481d51f1c3c","entry":"flip_words_in_prompt","repo":"aaquib111/acdcpp","repo_kind":"official","path":"ioi_task/ioi_dataset.py","file_url":"https://github.com/aaquib111/acdcpp/blob/HEAD/ioi_task/ioi_dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c8154481d51f1c3c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}