{"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/linear-explanations-for-individual-neurons","title":"Linear Explanations for Individual Neurons","arxiv_id":"2405.06855","date":"2024-05-10","proceeding":null,"authors":["Tuomas Oikarinen","Tsui-Wei Weng"],"abstract":"In recent years many methods have been developed to understand the internal workings of neural networks, often by describing the function of individual neurons in the model. However, these methods typically only focus on explaining the very highest activations of a neuron. In this paper we show this is not sufficient, and that the highest activation range is only responsible for a very small percentage of the neuron's causal effect. In addition, inputs causing lower activations are often very different and can't be reliably predicted by only looking at high activations. We propose that neurons should instead be understood as a linear combination of concepts, and develop an efficient method for producing these linear explanations. In addition, we show how to automatically evaluate description quality using simulation, i.e. predicting neuron activations on unseen inputs in vision setting.","url_abs":"https://arxiv.org/abs/2405.06855v1","url_pdf":"https://arxiv.org/pdf/2405.06855v1.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":"linear-explanations-for-individual-neurons","repo_url":"https://github.com/Trustworthy-ML-Lab/Linear-Explanations","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.06855","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.06855"}},"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":"deterministic:regex_extraction","url":"https://github.com/Trustworthy-ML-Lab/Linear-Explanations","reach":null}],"summary":{"ran_draft_wrong":6,"ran_honours":3,"unverified":2},"by_repo_kind":{"official":{"samples":11,"ran":9,"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":11,"samples":[{"code_sha256_prefix":"5c7687ca2ffbdd60","entry":"elastic_loss_and_acc","repo":"Trustworthy-ML-Lab/Linear-Explanations","repo_kind":"official","path":"linear_explanation.py","file_url":"https://github.com/Trustworthy-ML-Lab/Linear-Explanations/blob/HEAD/linear_explanation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5c7687ca2ffbdd60"}},{"code_sha256_prefix":"933fa162a2828c04","entry":"elastic_loss_and_acc_loader","repo":"Trustworthy-ML-Lab/Linear-Explanations","repo_kind":"official","path":"linear_explanation.py","file_url":"https://github.com/Trustworthy-ML-Lab/Linear-Explanations/blob/HEAD/linear_explanation.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":"933fa162a2828c04"}},{"code_sha256_prefix":"406014b884a2aaa7","entry":"get_device","repo":"Trustworthy-ML-Lab/Linear-Explanations","repo_kind":"official","path":"linear_explanation.py","file_url":"https://github.com/Trustworthy-ML-Lab/Linear-Explanations/blob/HEAD/linear_explanation.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":"406014b884a2aaa7"}},{"code_sha256_prefix":"6bf94bee8741ddb9","entry":"group_threshold","repo":"Trustworthy-ML-Lab/Linear-Explanations","repo_kind":"official","path":"linear_explanation.py","file_url":"https://github.com/Trustworthy-ML-Lab/Linear-Explanations/blob/HEAD/linear_explanation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6bf94bee8741ddb9"}},{"code_sha256_prefix":"eae0b64c4f002409","entry":"group_threshold_with_shrinkage","repo":"Trustworthy-ML-Lab/Linear-Explanations","repo_kind":"official","path":"linear_explanation.py","file_url":"https://github.com/Trustworthy-ML-Lab/Linear-Explanations/blob/HEAD/linear_explanation.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eae0b64c4f002409"}},{"code_sha256_prefix":"28bd63a25ca690f6","entry":"maximum_reg_loader","repo":"Trustworthy-ML-Lab/Linear-Explanations","repo_kind":"official","path":"linear_explanation.py","file_url":"https://github.com/Trustworthy-ML-Lab/Linear-Explanations/blob/HEAD/linear_explanation.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"28bd63a25ca690f6"}},{"code_sha256_prefix":"bfe4b187a1c5aeaf","entry":"soft_threshold","repo":"Trustworthy-ML-Lab/Linear-Explanations","repo_kind":"official","path":"linear_explanation.py","file_url":"https://github.com/Trustworthy-ML-Lab/Linear-Explanations/blob/HEAD/linear_explanation.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bfe4b187a1c5aeaf"}},{"code_sha256_prefix":"9fe33b70d272646e","entry":"soft_threshold_with_shrinkage","repo":"Trustworthy-ML-Lab/Linear-Explanations","repo_kind":"official","path":"linear_explanation.py","file_url":"https://github.com/Trustworthy-ML-Lab/Linear-Explanations/blob/HEAD/linear_explanation.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9fe33b70d272646e"}},{"code_sha256_prefix":"0b9235d47974092e","entry":"train_saga","repo":"Trustworthy-ML-Lab/Linear-Explanations","repo_kind":"official","path":"linear_explanation.py","file_url":"https://github.com/Trustworthy-ML-Lab/Linear-Explanations/blob/HEAD/linear_explanation.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":"0b9235d47974092e"}},{"code_sha256_prefix":"aed1ef1270b1463b","entry":"glm_saga","repo":"Trustworthy-ML-Lab/Linear-Explanations","repo_kind":"official","path":"linear_explanation.py","file_url":"https://github.com/Trustworthy-ML-Lab/Linear-Explanations/blob/HEAD/linear_explanation.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":"aed1ef1270b1463b"}},{"code_sha256_prefix":"fa8f500be0f1bfae","entry":"train_glm_model","repo":"Trustworthy-ML-Lab/Linear-Explanations","repo_kind":"official","path":"linear_explanation.py","file_url":"https://github.com/Trustworthy-ML-Lab/Linear-Explanations/blob/HEAD/linear_explanation.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":"fa8f500be0f1bfae"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}