Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Dense SAE Latents Are Features, Not Bugs
Xiaoqing Sun, Alessandro Stolfo, Joshua Engels +4
Sparse autoencoders (SAEs) are designed to extract interpretable features from language models by enforcing a sparsity constraint. Ideally, training an SAE would yield latents that…
cs.LG2025
MIB: A Mechanistic Interpretability Benchmark
Aaron Mueller, Atticus Geiger, Sarah Wiegreffe +20
How can we know whether new mechanistic interpretability methods achieve real improvements? In pursuit of lasting evaluation standards, we propose MIB, a Mechanistic Interpretabili…
cs.LG2024
Confidence Regulation Neurons in Language Models
Alessandro Stolfo, Ben Wu, Wes Gurnee +4
Despite their widespread use, the mechanisms by which large language models (LLMs) represent and regulate uncertainty in next-token predictions remain largely unexplored. This stud…