A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tang, Yiming, Saini, Harshvardhan, Yao, Zhaoqian, Lin, Zheng, Liao, Yizhen, Cui, Jingyi, Wang, Yisen, Du, Mengnan, Liu, Dianbo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!