{"url":"/sota/interpretability-techniques-for-deep-learning","task":{"name":"Interpretability Techniques for Deep Learning","url":"/task/interpretability-techniques-for-deep-learning","note":null},"dataset":{"name":"CausalGym","url":"/dataset/causalgym"},"category":"Miscellaneous","categories":["Miscellaneous"],"category_note":null,"description":null,"description_from":null,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Log odds-ratio (pythia-6.9b)"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Log odds-ratio (pythia-6.9b)":null}},"counts":{"rows":7,"rows_with_code":7,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"DAS","metrics":{"Log odds-ratio (pythia-6.9b)":"9.95"},"uses_additional_data":false,"paper_date":"2024-02-19","paper":"/paper/causalgym-benchmarking-causal","paper_url":"https://arxiv.org/abs/2402.12560v1","paper_title":"CausalGym: Benchmarking causal interpretability methods on linguistic tasks","code":"https://github.com/aryamanarora/causalgym","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":2,"model":"Linear probe","metrics":{"Log odds-ratio (pythia-6.9b)":"3.42"},"uses_additional_data":false,"paper_date":"2024-02-19","paper":"/paper/causalgym-benchmarking-causal","paper_url":"https://arxiv.org/abs/2402.12560v1","paper_title":"CausalGym: Benchmarking causal interpretability methods on linguistic tasks","code":"https://github.com/aryamanarora/causalgym","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":3,"model":"Difference-in-means","metrics":{"Log odds-ratio (pythia-6.9b)":"2.91"},"uses_additional_data":false,"paper_date":"2024-02-19","paper":"/paper/causalgym-benchmarking-causal","paper_url":"https://arxiv.org/abs/2402.12560v1","paper_title":"CausalGym: Benchmarking causal interpretability methods on linguistic tasks","code":"https://github.com/aryamanarora/causalgym","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":4,"model":"k-means","metrics":{"Log odds-ratio (pythia-6.9b)":"1.87"},"uses_additional_data":false,"paper_date":"2024-02-19","paper":"/paper/causalgym-benchmarking-causal","paper_url":"https://arxiv.org/abs/2402.12560v1","paper_title":"CausalGym: Benchmarking causal interpretability methods on linguistic tasks","code":"https://github.com/aryamanarora/causalgym","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":5,"model":"PCA","metrics":{"Log odds-ratio (pythia-6.9b)":"1.81"},"uses_additional_data":false,"paper_date":"2024-02-19","paper":"/paper/causalgym-benchmarking-causal","paper_url":"https://arxiv.org/abs/2402.12560v1","paper_title":"CausalGym: Benchmarking causal interpretability methods on linguistic tasks","code":"https://github.com/aryamanarora/causalgym","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":6,"model":"LDA","metrics":{"Log odds-ratio (pythia-6.9b)":"0.27"},"uses_additional_data":false,"paper_date":"2024-02-19","paper":"/paper/causalgym-benchmarking-causal","paper_url":"https://arxiv.org/abs/2402.12560v1","paper_title":"CausalGym: Benchmarking causal interpretability methods on linguistic tasks","code":"https://github.com/aryamanarora/causalgym","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":7,"model":"Random","metrics":{"Log odds-ratio (pythia-6.9b)":"0.01"},"uses_additional_data":false,"paper_date":"2024-02-19","paper":"/paper/causalgym-benchmarking-causal","paper_url":"https://arxiv.org/abs/2402.12560v1","paper_title":"CausalGym: Benchmarking causal interpretability methods on linguistic tasks","code":"https://github.com/aryamanarora/causalgym","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}}],"since_archive":{"present":false,"note":"No Syntology-extracted rows are published in this build."},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":7,"rows_with_any_sample_ran":7,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":14,"n_unverified":0,"n_samples":14,"n_pointer_only_licence":14,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}