Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment

6 February 2025

Papers citing "Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment"

6 / 6 papers shown

Title
Interpreting the Linear Structure of Vision-language Model Embedding Spaces Isabel Papadimitriou Huangyuan Su Thomas Fel Naomi Saphra Sham Kakade Stephanie Gil VLM 35 0 0 16 Apr 2025
Robustly identifying concepts introduced during chat fine-tuning using crosscoders Julian Minder Clement Dumas Caden Juang Bilal Chugtai Neel Nanda 19 0 0 03 Apr 2025
Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models Mateusz Pach Shyamgopal Karthik Quentin Bouniot Serge Belongie Zeynep Akata VLM 54 0 0 03 Apr 2025
Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry Sai Sumedh R. Hindupur Ekdeep Singh Lubana Thomas Fel Demba Ba 29 4 0 03 Mar 2025
Mind the Gap: Bridging the Divide Between AI Aspirations and the Reality of Autonomous Characterization Grace Guinan Addison Salvador Michelle A. Smeaton Andrew Glaws Hilary Egan Brian C. Wyatt Babak Anasori K. Fiedler M. Olszta Steven Spurgeon 58 0 0 25 Feb 2025
Sparse Autoencoders Reveal Universal Feature Spaces Across Large Language Models Michael Lan Philip H. S. Torr Austin Meek Ashkan Khakzar David M. Krueger Fazl Barez 25 9 0 09 Oct 2024