Speaker: Onkar Gujral Title: Mechanistic interpretability of science-AI models Abstract: AI models trained for biological tasks, such as protein language models, get used for a wide variety of high-stakes downstream applications like drug discovery. But we can’t see what these models are doing internally, which makes them opaque blackboxes, hindering trust and explainability in applications. We will describe our work on applying sparse dictionary learning methods to interpret protein language models. This approach disentangles their internal representations into human-understandable biologica…
Open this event on awaresie to see it on the map, get directions, RSVP and chat with the other guests - no account needed.
More things to do in Boston, MA
Plan and gather with your community - private by design. No account needed, no password, no tracking cookies.