{"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/the-elephant-in-the-interpretability-room-why","title":"The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?","arxiv_id":"2010.05607","date":"2020-10-12","proceeding":"EMNLP (BlackboxNLP) 2020 11","authors":["Jasmijn Bastings","Katja Filippova"],"abstract":"There is a recent surge of interest in using attention as explanation of model predictions, with mixed evidence on whether attention can be used as such. While attention conveniently gives us one weight per input token and is easily extracted, it is often unclear toward what goal it is used as explanation. We find that often that goal, whether explicitly stated or not, is to find out what input tokens are the most relevant to a prediction, and that the implied user for the explanation is a model developer. For this goal and user, we argue that input saliency methods are better suited, and that there are no compelling reasons to use attention, despite the coincidence that it provides a weight for each input. With this position paper, we hope to shift some of the recent focus on attention to saliency methods, and for authors to clearly state the goal and user for their explanations.","url_abs":"https://arxiv.org/abs/2010.05607v1","url_pdf":"https://arxiv.org/pdf/2010.05607v1.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":"the-elephant-in-the-interpretability-room-why","repo_url":"https://github.com/jessevig/bertviz","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.05607","atlas_url":"https://app.syntology.ai/?focus=2010.05607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.05607"}},"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/jessevig/bertviz","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":6,"ran_honours":1,"unverified":9},"by_repo_kind":{"listed":{"samples":16,"ran":7,"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":0,"samples":[{"code_sha256_prefix":"0f786c407fb1ee4c","entry":"swish","repo":"jessevig/bertviz","repo_kind":"listed","path":"bertviz/transformers_neuron_view/modeling_bert.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_bert.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0f786c407fb1ee4c"}},{"code_sha256_prefix":"35ef111fc00c21b4","entry":"build_tf_to_pytorch_map","repo":"jessevig/bertviz","repo_kind":"listed","path":"bertviz/transformers_neuron_view/modeling_transfo_xl.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_transfo_xl.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"35ef111fc00c21b4"}},{"code_sha256_prefix":"11442089a6433797","entry":"format_special_chars","repo":"jessevig/bertviz","repo_kind":"listed","path":"bertviz/neuron_view.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/neuron_view.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"11442089a6433797"}},{"code_sha256_prefix":"fdc64f4c72036ae4","entry":"gelu","repo":"jessevig/bertviz","repo_kind":"listed","path":"bertviz/transformers_neuron_view/modeling_bert.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_bert.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"code_sha256_prefix":"0c145728a35789fa","entry":"load_tf_weights_in_bert","repo":"jessevig/bertviz","repo_kind":"listed","path":"bertviz/transformers_neuron_view/modeling_bert.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_bert.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0c145728a35789fa"}},{"code_sha256_prefix":"d30d6c3098df2c42","entry":"prune_linear_layer","repo":"jessevig/bertviz","repo_kind":"listed","path":"bertviz/transformers_neuron_view/modeling_utils.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d30d6c3098df2c42"}},{"code_sha256_prefix":"93228a3eb5c4d179","entry":"sample_logits","repo":"jessevig/bertviz","repo_kind":"listed","path":"bertviz/transformers_neuron_view/modeling_transfo_xl_utilities.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_transfo_xl_utilities.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"93228a3eb5c4d179"}},{"code_sha256_prefix":"c92ba449e48ecffe","entry":"build_tf_xlnet_to_pytorch_map","repo":"jessevig/bertviz","repo_kind":"listed","path":"bertviz/transformers_neuron_view/modeling_xlnet.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_xlnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c92ba449e48ecffe"}},{"code_sha256_prefix":"d4eae117e16a3f41","entry":"get_attention","repo":"jessevig/bertviz","repo_kind":"listed","path":"bertviz/neuron_view.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/neuron_view.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d4eae117e16a3f41"}},{"code_sha256_prefix":"f5d8d44f65a08b76","entry":"get_masks","repo":"jessevig/bertviz","repo_kind":"listed","path":"bertviz/transformers_neuron_view/modeling_xlm.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_xlm.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f5d8d44f65a08b76"}},{"code_sha256_prefix":"654e91efc679fe84","entry":"load_tf_weights_in_gpt2","repo":"jessevig/bertviz","repo_kind":"listed","path":"bertviz/transformers_neuron_view/modeling_gpt2.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_gpt2.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"654e91efc679fe84"}},{"code_sha256_prefix":"42ee168c3ae12e60","entry":"load_tf_weights_in_openai_gpt","repo":"jessevig/bertviz","repo_kind":"listed","path":"bertviz/transformers_neuron_view/modeling_openai.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_openai.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"42ee168c3ae12e60"}},{"code_sha256_prefix":"23d246e59ef9447b","entry":"load_tf_weights_in_transfo_xl","repo":"jessevig/bertviz","repo_kind":"listed","path":"bertviz/transformers_neuron_view/modeling_transfo_xl.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_transfo_xl.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"23d246e59ef9447b"}},{"code_sha256_prefix":"4a94662ff3b5c5cf","entry":"load_tf_weights_in_xlnet","repo":"jessevig/bertviz","repo_kind":"listed","path":"bertviz/transformers_neuron_view/modeling_xlnet.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_xlnet.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4a94662ff3b5c5cf"}},{"code_sha256_prefix":"7183a17dd79327a8","entry":"prune_conv1d_layer","repo":"jessevig/bertviz","repo_kind":"listed","path":"bertviz/transformers_neuron_view/modeling_utils.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7183a17dd79327a8"}},{"code_sha256_prefix":"e31093ffc8275cff","entry":"prune_layer","repo":"jessevig/bertviz","repo_kind":"listed","path":"bertviz/transformers_neuron_view/modeling_utils.py","file_url":"https://github.com/jessevig/bertviz/blob/HEAD/bertviz/transformers_neuron_view/modeling_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e31093ffc8275cff"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}