[2405.07987] The Platonic Representation Hypothesis

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. arXiv Operational Status Get status notifications via email or slack

[2405.07987] The Platonic Representation Hypothesis Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Machine Learning arXiv:2405.07987 (cs) [Submitted on 13 May 2024 ( v1 ), last revised 25 Jul 2024 (this version, v5)] Title: The Platonic Representation Hypothesis Authors: Minyoung Huh , Brian Cheung , Tongzhou Wang , Phillip Isola View a PDF of the paper titled The Platonic Representation Hypothesis, by Minyoung Huh and 3 other authors View PDF HTML (experimental) Abstract: We argu

related reading

• The Platonic Representation Hypothesisphillipi.github.io
• The Platonic Representation Hypothesisarxiv.org
• All AI Models Might Be The Same - by Jack Morrisblog.jxmo.io
• The Scaling Hypothesis · Gwern.netgwern.net
• The “it” in AI models is the dataset. — Non_Intnonint.com
• Interpretability Dreamstransformer-circuits.pub
• 2310.01405.pdfarxiv.org
• 2310.01405arxiv.org
• The Linear Representation Hypothesis and the Geometry of Large Language Modelsarxiv.org
• Formation of Representations in Neural Networksarxiv.org
• Actually, Othello-GPT Has A Linear Emergent World Representation - Neel Nandaneelnanda.io
• [2210.13382] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskarxiv.org