{"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/toy-models-of-superposition","title":"Toy Models of Superposition","arxiv_id":"2209.10652","date":"2022-09-21","proceeding":null,"authors":["Nelson Elhage","Tristan Hume","Catherine Olsson","Nicholas Schiefer","Tom Henighan","Shauna Kravec","Zac Hatfield-Dodds","Robert Lasenby","Dawn Drain","Carol Chen","Roger Grosse","Sam McCandlish","Jared Kaplan","Dario Amodei","Martin Wattenberg","Christopher Olah"],"abstract":"Neural networks often pack many unrelated concepts into a single neuron - a puzzling phenomenon known as 'polysemanticity' which makes interpretability much more challenging. This paper provides a toy model where polysemanticity can be fully understood, arising as a result of models storing additional sparse features in \"superposition.\" We demonstrate the existence of a phase change, a surprising connection to the geometry of uniform polytopes, and evidence of a link to adversarial examples. We also discuss potential implications for mechanistic interpretability.","url_abs":"https://arxiv.org/abs/2209.10652v1","url_pdf":"https://arxiv.org/pdf/2209.10652v1.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":"toy-models-of-superposition","repo_url":"https://github.com/anthropics/toy-models-of-superposition","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2209.10652","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}