Skip to content
conftrace_
2025 ICML ICML 2025

Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Lucy Farnik, Tim Lawson, Conor Houghton, Laurence Aitchison

Topics

Artificial Intelligence > Core AI > Interpretability Machine Learning > Core Methods > Representation Learning Natural Language Processing > Resources & Methods > Large Language Models

Keywords

interpretability latent activation large language model computational sparsity jacobian sparse autoencoders sparsify computations
Download PDF