Heading to NeurIPS this week! Let me know if you want to chat about science of what models learn, cognitive science, interpretability, what models learn in context vs. from their training data, etc. A few things I'm involved in:

Large language models store vast amounts of knowledge, but how exactly do they learn it?

Excited to share my Google DeepMind internship results, which reveal the fascinating dynamics behind factual knowledge acquisition in LLMs!