Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability
Year: 2026
Type: preprint
Abstract: Sparse autoencoders (SAEs) decompose internal activations of neural networks into sparse linear combinations of learned features by fitting an overcomplete dictionary $\mathbf{W}\in\mathbb{R}^{m\times n}$ with $m
Source: arXiv (Cornell University)
Author: Mendoza-Smith, Rodrigo
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7167276265
Cites:
Cited by:
Related to: