{"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/from-neurons-to-neutrons-a-case-study-in","title":"From Neurons to Neutrons: A Case Study in Interpretability","arxiv_id":"2405.17425","date":"2024-05-27","proceeding":null,"authors":["Ouail Kitouni","Niklas Nolte","Víctor Samuel Pérez-Díaz","Sokratis Trifinopoulos","Mike Williams"],"abstract":"Mechanistic Interpretability (MI) promises a path toward fully understanding how neural networks make their predictions. Prior work demonstrates that even when trained to perform simple arithmetic, models can implement a variety of algorithms (sometimes concurrently) depending on initialization and hyperparameters. Does this mean neuron-level interpretability techniques have limited applicability? We argue that high-dimensional neural networks can learn low-dimensional representations of their training data that are useful beyond simply making good predictions. Such representations can be understood through the mechanistic interpretability lens and provide insights that are surprisingly faithful to human-derived domain knowledge. This indicates that such approaches to interpretability can be useful for deriving a new understanding of a problem from models trained to solve it. As a case study, we extract nuclear physics concepts by studying models trained to reproduce nuclear data.","url_abs":"https://arxiv.org/abs/2405.17425v1","url_pdf":"https://arxiv.org/pdf/2405.17425v1.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":"from-neurons-to-neutrons-a-case-study-in","repo_url":"https://github.com/samuelperezdi/nuclr-icml","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2405.17425","atlas_url":"https://app.syntology.ai/?focus=2405.17425","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.17425"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/samuelperezdi/nuclr-icml","reach":{"status":"ok"}}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"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":7,"samples":[{"code_sha256_prefix":"c951a7334429328e","entry":"BW2_mass_formula","repo":"samuelperezdi/nuclr-icml","repo_kind":"official","path":"src/data.py","file_url":"https://github.com/samuelperezdi/nuclr-icml/blob/HEAD/src/data.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":"c951a7334429328e"}},{"code_sha256_prefix":"02671e0b5bf98b52","entry":"delta","repo":"samuelperezdi/nuclr-icml","repo_kind":"official","path":"src/data.py","file_url":"https://github.com/samuelperezdi/nuclr-icml/blob/HEAD/src/data.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":"02671e0b5bf98b52"}},{"code_sha256_prefix":"5f49c1ebd2b79fd2","entry":"get_model_fn","repo":"samuelperezdi/nuclr-icml","repo_kind":"official","path":"src/model.py","file_url":"https://github.com/samuelperezdi/nuclr-icml/blob/HEAD/src/model.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":"5f49c1ebd2b79fd2"}},{"code_sha256_prefix":"b1cf097312f4832f","entry":"get_rms","repo":"samuelperezdi/nuclr-icml","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/samuelperezdi/nuclr-icml/blob/HEAD/src/utils.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":"b1cf097312f4832f"}},{"code_sha256_prefix":"8afd3cad72d99ad5","entry":"inverse_transform","repo":"samuelperezdi/nuclr-icml","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/samuelperezdi/nuclr-icml/blob/HEAD/src/utils.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":"8afd3cad72d99ad5"}},{"code_sha256_prefix":"46779ce3beb9fd30","entry":"shell","repo":"samuelperezdi/nuclr-icml","repo_kind":"official","path":"src/data.py","file_url":"https://github.com/samuelperezdi/nuclr-icml/blob/HEAD/src/data.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":"46779ce3beb9fd30"}},{"code_sha256_prefix":"a28a752bf116b1cf","entry":"preds_targets_zn","repo":"samuelperezdi/nuclr-icml","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/samuelperezdi/nuclr-icml/blob/HEAD/src/utils.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":"a28a752bf116b1cf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}