PRISM
Perspectives on Interpretability in Sciences and ML
A reading club systematically exploring the similarities and differences between neuroscience and machine learning interpretability.
The Nuts and Bolts of Understanding: Neurons, Circuits, Features, and Manifolds
A panel discussion bringing together neuroscientists and AI researchers to explore the fundamental units of neural computation — and what interpretability means across these levels of description.
Agenda: Opening — what are the units of computation? · Component deep-dives · Bridging across components and fields · Looking ahead into the future
Large Language Models Generate Harmful Content Using a Distinct, Unified Mechanism
A presentation on how harmful behavior in LLMs relies on a compact set of internal weights, helping explain why safety safeguards are brittle and why narrow fine-tuning can trigger broad misalignment.
PRISM sessions are open to all — graduate students, postdocs, undergraduates, and faculty across departments.
SEC, Harvard University, Cambridge MA
Tuesdays, 3:00–4:00 PM ET
Light refreshments provided.
