2 papers
cs.CL2026
Turn-Averaged SAEs for Feature Discovery and Long-Context Attribution
Kevin Der, Harish Kamath, Ben Thompson
Sparse autoencoders (SAEs) have become a useful tool for extracting interpretable features in language models. However, standard SAE architectures operate on individual token activ…
cs.AI2025
Aristotle: IMO-level Automated Theorem Proving
Tudor Achim, Alex Best, Alberto Bietti +20
We introduce Aristotle, an AI system that combines formal verification with informal reasoning, achieving gold-medal-equivalent performance on the 2025 International Mathematical O…