Mechanistic interpretability by applying dictionary learning to Distill-GPT-2

We investigate the utility of LLMs for supporting academic major advising and find it to be a promising area for Human-AI collaboration.

A toy educational app using language models to convert a document to slides for a 10-year old to learn from.

Blog proceedings of UVA’s Fall 2023 Seminar ‘Risks (and Benefits) of Generative AI and Large Language Models’