{"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/lm-transparency-tool-interactive-tool-for","title":"LM Transparency Tool: Interactive Tool for Analyzing Transformer Language Models","arxiv_id":"2404.07004","date":"2024-04-10","proceeding":null,"authors":["Igor Tufanov","Karen Hambardzumyan","Javier Ferrando","Elena Voita"],"abstract":"We present the LM Transparency Tool (LM-TT), an open-source interactive toolkit for analyzing the internal workings of Transformer-based language models. Differently from previously existing tools that focus on isolated parts of the decision-making process, our framework is designed to make the entire prediction process transparent, and allows tracing back model behavior from the top-layer representation to very fine-grained parts of the model. Specifically, it (1) shows the important part of the whole input-to-output information flow, (2) allows attributing any changes done by a model block to individual attention heads and feed-forward neurons, (3) allows interpreting the functions of those heads or neurons. A crucial part of this pipeline is showing the importance of specific model components at each step. As a result, we are able to look at the roles of model components only in cases where they are important for a prediction. Since knowing which components should be inspected is key for analyzing large models where the number of these components is extremely high, we believe our tool will greatly support the interpretability community both in research settings and in practical applications.","url_abs":"https://arxiv.org/abs/2404.07004v1","url_pdf":"https://arxiv.org/pdf/2404.07004v1.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":"lm-transparency-tool-interactive-tool-for","repo_url":"https://github.com/facebookresearch/llm-transparency-tool","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.07004","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.07004"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/llm-transparency-tool","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":4},"by_repo_kind":{"listed":{"samples":4,"ran":4,"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":4,"samples":[{"code_sha256_prefix":"38a027005fb1427f","entry":"build_paths_to_predictions","repo":"facebookresearch/llm-transparency-tool","repo_kind":"listed","path":"llm_transparency_tool/routes/graph.py","file_url":"https://github.com/facebookresearch/llm-transparency-tool/blob/HEAD/llm_transparency_tool/routes/graph.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"38a027005fb1427f"}},{"code_sha256_prefix":"78556e0a43684f3a","entry":"load_dataset","repo":"facebookresearch/llm-transparency-tool","repo_kind":"listed","path":"llm_transparency_tool/server/utils.py","file_url":"https://github.com/facebookresearch/llm-transparency-tool/blob/HEAD/llm_transparency_tool/server/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"78556e0a43684f3a"}},{"code_sha256_prefix":"f3a3389859fa9845","entry":"logits_color_map","repo":"facebookresearch/llm-transparency-tool","repo_kind":"listed","path":"llm_transparency_tool/server/styles.py","file_url":"https://github.com/facebookresearch/llm-transparency-tool/blob/HEAD/llm_transparency_tool/server/styles.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f3a3389859fa9845"}},{"code_sha256_prefix":"ac8371c19e22def5","entry":"string_to_display","repo":"facebookresearch/llm-transparency-tool","repo_kind":"listed","path":"llm_transparency_tool/server/styles.py","file_url":"https://github.com/facebookresearch/llm-transparency-tool/blob/HEAD/llm_transparency_tool/server/styles.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ac8371c19e22def5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}