SURF Mentoring

Potential projects/topics: Exploring Language Model Interpretability. This project investigates how language models work internally, focusing on components like neurons, activations and attention heads. Students will analyze model behavior, build interpretability tools, and gain foundational skills in AI research, offering a comprehensive understanding of how these systems process information and make predictions.

Potential skills gained: AI/ML basic knowledge, research skill, Python ML packages programming

Required qualifications or skills: Basic Statistics and Programming skills. Optional but helpful: familiarity with AI/ML concepts.

Direct mentor: Graduate Student