works on
benchmark dataset 1large language models 1software security 1static analysis 1vulnerability detection 1

From the 1 of 2 linked papers with an AI index.

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2025

A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders

David Chanin, James Wilken-Smith, Tomáš Dulka +3

Sparse Autoencoders (SAEs) aim to decompose the activation space of large language models (LLMs) into human-interpretable latent directions or features. As we increase the number o…