{"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/have-faith-in-faithfulness-going-beyond","title":"Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms","arxiv_id":"2403.17806","date":"2024-03-26","proceeding":null,"authors":["Michael Hanna","Sandro Pezzelle","Yonatan Belinkov"],"abstract":"Many recent language model (LM) interpretability studies have adopted the circuits framework, which aims to find the minimal computational subgraph, or circuit, that explains LM behavior on a given task. Most studies determine which edges belong in a LM's circuit by performing causal interventions on each edge independently, but this scales poorly with model size. Edge attribution patching (EAP), gradient-based approximation to interventions, has emerged as a scalable but imperfect solution to this problem. In this paper, we introduce a new method - EAP with integrated gradients (EAP-IG) - that aims to better maintain a core property of circuits: faithfulness. A circuit is faithful if all model edges outside the circuit can be ablated without changing the model's performance on the task; faithfulness is what justifies studying circuits, rather than the full model. Our experiments demonstrate that circuits found using EAP are less faithful than those found using EAP-IG, even though both have high node overlap with circuits found previously using causal interventions. We conclude more generally that when using circuits to compare the mechanisms models use to solve tasks, faithfulness, not overlap, is what should be measured.","url_abs":"https://arxiv.org/abs/2403.17806v2","url_pdf":"https://arxiv.org/pdf/2403.17806v2.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":"have-faith-in-faithfulness-going-beyond","repo_url":"https://github.com/hannamw/eap-ig","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"have-faith-in-faithfulness-going-beyond","repo_url":"https://github.com/hannamw/eap-ig-faithfulness","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"have-faith-in-faithfulness-going-beyond","repo_url":"https://github.com/zjunlp/knowledgecircuits","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"patching","method_name":"Patching"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.17806","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17806"}},"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/hannamw/eap-ig","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hannamw/eap-ig-faithfulness","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zjunlp/knowledgecircuits","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"dd9a8fe605582899","entry":"display_name","repo":"hannamw/eap-ig-faithfulness","repo_kind":"official","path":"results/first_figure/first_figure.py","file_url":"https://github.com/hannamw/eap-ig-faithfulness/blob/HEAD/results/first_figure/first_figure.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":"dd9a8fe605582899"}},{"code_sha256_prefix":"868d5a57fcee7fea","entry":"task_to_metric","repo":"hannamw/eap-ig-faithfulness","repo_kind":"official","path":"results/first_figure/first_figure.py","file_url":"https://github.com/hannamw/eap-ig-faithfulness/blob/HEAD/results/first_figure/first_figure.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"868d5a57fcee7fea"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}