Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines? Paper • 2602.14111 • Published 18 days ago • 55
Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities Paper • 2602.05281 • Published 29 days ago • 14
bAbI Collection bAbI qa1-5 tasks from Weston, Jason, et al. "Towards ai-complete question answering: A set of prerequisite toy tasks." arXiv preprint arXiv:1502.05698 • 5 items • Updated Dec 26, 2025