{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/looking-beyond-the-top-1-transformers","title":"Looking Beyond The Top-1: Transformers Determine Top Tokens In Order","arxiv_id":"2410.20210","date":"2024-10-26","proceeding":null,"authors":["Daria Lioubashevski","Tomer Schlank","Gabriel Stanovsky","Ariel Goldstein"],"abstract":"Understanding the inner workings of Transformers is crucial for achieving more accurate and efficient predictions. In this work, we analyze the computation performed by Transformers in the layers after the top-1 prediction has become fixed, which has been previously referred to as the \"saturation event\". We expand the concept of saturation events for top-k tokens, demonstrating that similar saturation events occur across language, vision, and speech models. We find that these saturation events happen in order of the corresponding tokens' ranking, i.e., the model first decides on the top ranking token, then the second highest ranking token, and so on. This phenomenon seems intrinsic to the Transformer architecture, occurring across different architectural variants (decoder-only, encoder-only, and to a lesser extent full-Transformer), and even in untrained Transformers. We propose an underlying mechanism of task transition for this sequential saturation, where task k corresponds to predicting the k-th most probable token, and the saturation events are in fact discrete transitions between the tasks. In support of this we show that it is possible to predict the current task from hidden layer embedding. Furthermore, using an intervention method we demonstrate that we can cause the model to switch from one task to the next. Finally, leveraging our findings, we introduce a novel token-level early-exit strategy, which surpasses existing methods in balancing performance and efficiency.","url_abs":"https://arxiv.org/abs/2410.20210v1","url_pdf":"https://arxiv.org/pdf/2410.20210v1.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":"looking-beyond-the-top-1-transformers","repo_url":"https://github.com/daria-lioubashevski/beyond_top1","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.20210","atlas_url":"https://app.syntology.ai/?focus=2410.20210","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.20210"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.20210"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2410.20210"},"call":"get_harvested_code_for_paper(arxiv_id=\"2410.20210\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2410.20210"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2410.20210\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2410.20210"},"call":"get_concepts_for_paper(arxiv_id=\"2410.20210\")"}],"by_repo":[{"repo":"daria-lioubashevski/beyond_top1","kind":"official","samples":11,"ran":10,"instrument":1,"unverified":1}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2410.20210.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2410.20210.svg"},"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/daria-lioubashevski/beyond_top1","reach":{"status":"ok"}}],"summary":{"ran":7,"ran_honours":1,"ran_violates":1,"ran_fixture":1,"unverified":1},"n_samples":11,"n_ran":10,"n_constructed":0,"n_ran_checked":9,"n_instrument":1,"n_unverified":1,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":11,"ran":10,"n_ran_checked":9,"n_instrument":1,"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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":10,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-26","last":"2026-09-26","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"7da5b38013b578c8","code_sha256_prefix":"7da5b38013b578c8","entry":"calc_num_tokens_per_sample_whisper","repo":"daria-lioubashevski/beyond_top1","repo_kind":"official","path":"utils.py","file_url":"https://github.com/daria-lioubashevski/beyond_top1/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"processor:StandInProcessor/0/?, samples:list/1/dict","fixture_out_type":"list","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, daria-lioubashevski/beyond_top1 when it was checked","mcp_get_code":{"code_sha256":"7da5b38013b578c8"}},{"code_sha256":"1843b02bc60b8266","code_sha256_prefix":"1843b02bc60b8266","entry":"calc_rank_from_satur_layers_arr","repo":"daria-lioubashevski/beyond_top1","repo_kind":"official","path":"analysis/order_of_saturation_layer_analysis.py","file_url":"https://github.com/daria-lioubashevski/beyond_top1/blob/HEAD/analysis/order_of_saturation_layer_analysis.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"saturation_layer_arr:ndarray/2/float, num_layers:int/0/int, k:int/0/int","fixture_out_type":"defaultdict","level_recorded_at":"2026-09-26T01:55:17.694675+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, daria-lioubashevski/beyond_top1 when it was checked","mcp_get_code":{"code_sha256":"1843b02bc60b8266"}},{"code_sha256":"dfd02530798f1bab","code_sha256_prefix":"dfd02530798f1bab","entry":"calculate_accuracy","repo":"daria-lioubashevski/beyond_top1","repo_kind":"official","path":"practical_applications/new_early_exit.py","file_url":"https://github.com/daria-lioubashevski/beyond_top1/blob/HEAD/practical_applications/new_early_exit.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"preds:ndarray/1/int, true_labels:ndarray/1/int","fixture_out_type":"float64","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","retrieve_with":{"tool":"get_code","code_sha256":"dfd02530798f1bab"},"code_page":"/code/calculate-accuracy","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, daria-lioubashevski/beyond_top1 when it was checked","mcp_get_code":{"code_sha256":"dfd02530798f1bab"}},{"code_sha256":"98fff0501f6ae3af","code_sha256_prefix":"98fff0501f6ae3af","entry":"calculate_proportion_test","repo":"daria-lioubashevski/beyond_top1","repo_kind":"official","path":"practical_applications/better_language_modeling.py","file_url":"https://github.com/daria-lioubashevski/beyond_top1/blob/HEAD/practical_applications/better_language_modeling.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"n1:int/0/int, x1:int/0/int, n2:int/0/int, x2:int/0/int","fixture_out_type":"float64","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","retrieve_with":{"tool":"get_code","code_sha256":"98fff0501f6ae3af"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, daria-lioubashevski/beyond_top1 when it was checked","mcp_get_code":{"code_sha256":"98fff0501f6ae3af"}},{"code_sha256":"450f8cb37067b75b","code_sha256_prefix":"450f8cb37067b75b","entry":"calculate_speedup","repo":"daria-lioubashevski/beyond_top1","repo_kind":"official","path":"practical_applications/new_early_exit.py","file_url":"https://github.com/daria-lioubashevski/beyond_top1/blob/HEAD/practical_applications/new_early_exit.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"total_layers:int/0/int, layer_counts:ndarray/1/int","fixture_out_type":"float64","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, daria-lioubashevski/beyond_top1 when it was checked","mcp_get_code":{"code_sha256":"450f8cb37067b75b"}},{"code_sha256":"f031dfe3a7ed9d02","code_sha256_prefix":"f031dfe3a7ed9d02","entry":"create_random_features","repo":"daria-lioubashevski/beyond_top1","repo_kind":"official","path":"analysis/run_task_transition_probing.py","file_url":"https://github.com/daria-lioubashevski/beyond_top1/blob/HEAD/analysis/run_task_transition_probing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"features:ndarray/2/float, labels:ndarray/1/int, num_classes:int/0/int","fixture_out_type":"ndarray","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, daria-lioubashevski/beyond_top1 when it was checked","mcp_get_code":{"code_sha256":"f031dfe3a7ed9d02"}},{"code_sha256":"fe90e5419c374fc4","code_sha256_prefix":"fe90e5419c374fc4","entry":"get_train_test_indxs","repo":"daria-lioubashevski/beyond_top1","repo_kind":"official","path":"analysis/run_task_transition_probing.py","file_url":"https://github.com/daria-lioubashevski/beyond_top1/blob/HEAD/analysis/run_task_transition_probing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"kfolds:int/0/int, folds:list/1/ndarray, i:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, daria-lioubashevski/beyond_top1 when it was checked","mcp_get_code":{"code_sha256":"fe90e5419c374fc4"}},{"code_sha256":"7a9e1de7487a1b1d","code_sha256_prefix":"7a9e1de7487a1b1d","entry":"hook_fn_vit","repo":"daria-lioubashevski/beyond_top1","repo_kind":"official","path":"intervention/run_intervention_procedure.py","file_url":"https://github.com/daria-lioubashevski/beyond_top1/blob/HEAD/intervention/run_intervention_procedure.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"module:callable/0/?, inputs:tuple/1/Tensor, outputs:Tensor/3/float, new_vector:Tensor/2/float","fixture_out_type":"tuple","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, daria-lioubashevski/beyond_top1 when it was checked","mcp_get_code":{"code_sha256":"7a9e1de7487a1b1d"}},{"code_sha256":"29cee21e44ff74bf","code_sha256_prefix":"29cee21e44ff74bf","entry":"is_concordant_strict","repo":"daria-lioubashevski/beyond_top1","repo_kind":"official","path":"analysis/order_of_saturation_layer_analysis.py","file_url":"https://github.com/daria-lioubashevski/beyond_top1/blob/HEAD/analysis/order_of_saturation_layer_analysis.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"pair:tuple/1/int, ls1:list/1/float, ls2:list/1/float","fixture_out_type":"bool","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, daria-lioubashevski/beyond_top1 when it was checked","mcp_get_code":{"code_sha256":"29cee21e44ff74bf"}},{"code_sha256":"1d34728c3d0ae06a","code_sha256_prefix":"1d34728c3d0ae06a","entry":"ktau_strict","repo":"daria-lioubashevski/beyond_top1","repo_kind":"official","path":"analysis/order_of_saturation_layer_analysis.py","file_url":"https://github.com/daria-lioubashevski/beyond_top1/blob/HEAD/analysis/order_of_saturation_layer_analysis.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"signature":"ls1:list/1/int, ls2:list/1/int","fixture_out_type":"float","level_recorded_at":"2026-09-26T01:24:49.973517+00:00","retrieve_with":{"tool":"get_code","code_sha256":"1d34728c3d0ae06a"},"code_page":null,"census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, daria-lioubashevski/beyond_top1 when it was checked","mcp_get_code":{"code_sha256":"1d34728c3d0ae06a"}},{"code_sha256":"c8ae8abf0a896cb6","code_sha256_prefix":"c8ae8abf0a896cb6","entry":"load_samples","repo":"daria-lioubashevski/beyond_top1","repo_kind":"official","path":"utils.py","file_url":"https://github.com/daria-lioubashevski/beyond_top1/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/load-samples","census":null,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, daria-lioubashevski/beyond_top1 when it was checked","mcp_get_code":{"code_sha256":"c8ae8abf0a896cb6"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"4a9d7e11ed2a9ee944b58bd51d6cdaef76a248e39bde8f93a7a29660c5197462","record_changed_at":"2026-10-04","record_changed_at_basis":"changed"}