The Persian Rug: solving toy models of superposition using large-scale symmetries

15 October 2024

Papers citing "The Persian Rug: solving toy models of superposition using large-scale symmetries"

5 / 5 papers shown

Title
Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models Samuel Marks Can Rager Eric J. Michaud Yonatan Belinkov David Bau Aaron Mueller 111 146 0 28 Mar 2024
Dynamical versus Bayesian Phase Transitions in a Toy Model of Superposition Zhongtian Chen Edmund Lau Jake Mendel Susan Wei Daniel Murfet 41 15 0 10 Oct 2023
Locating and Editing Factual Associations in GPT Kevin Meng David Bau A. Andonian Yonatan Belinkov KELM 220 1,344 0 10 Feb 2022
From Principal Subspaces to Principal Components with Linear Autoencoders Elad Plaut SSL 36 115 0 26 Apr 2018
Statistical Mechanics of Dictionary Learning A. Sakata Y. Kabashima 72 25 0 28 Mar 2012