Hey there! I'm a research fellow at the Cambridge-Boston Alignment Initiative, working with Aaron Mueller. Before this, I was a predoctoral researcher at UT Austin with Kyle Mahowald. And even before that, I was an undergrad at UC Berkeley 🐻, where I was fortunate to get my start in research with Alane Suhr. I have also interned at CMU LTI (with Graham Neubig) and the MIT Lincoln Lab.
Research interests
Nowadays, I mostly work on the interpretability of language models, with a focus on explanations rooted in data, learning, and representation. I'm particularly interested in questions and phenomena that have natural implications for our ability to control and align models. I often draw inspiration from more mature fields (e.g., cognitive science, linguistics, physics) that have made progress in understanding by developing simple, but principled, models of more complex systems.
“All models are wrong, but some are useful.”