My research focuses on language model interpretability and representation engineering. I believe that interpretability has incredibly diverse applications from helping understand and fix known limitations of models to improving explainability and safety. I am generally interested in all interpretability and representation engineering-based research, especially directions with concrete applications.

I'm also interested in language model evals and various other alignment problems.

I work in the Oxford Internet Institute's language modelling group, supervised by Dr Adam Mahdi, and am also a member of OxNLP.
‍

I'm a PhD student at the University of Oxford researching large language models. I'm broadly interested in the interpretability of models and representation engineering, which involves exploring how our understanding of language model intermediate representations can be concretely applied to useful downstream tasks.

I'm a member of the Oxford Internet Institute's new language modelling group as well as the OxNLP reading group. Feel free to reach out if you would like to chat about research, teaching, talks or more!

Coming soon...