During his PhD at Brown University, he focused on the interpretability of language models.
Education
PhD: Brown University, advised by Ellie Pavlick and Carsten Eickhoff; BS: UMass Amherst, where he worked with Mohit Iyyer and Brendan O’Connor on NLP and computational social science problems.
Background
Research interests: interpreting the processes language models use to make predictions and the kinds of structure that can be learned from self-supervised learning. Current focus is using and developing tools in mechanistic interpretability to shed light on how language models perform complex behaviors.
Miscellany
You can reach him at first-name_last-name at brown.edu.