Published several papers or articles including but not limited to: 'Sparse Feature Circuits', 'LLM benchmark with board games', 'Automatic Circuit Discovery', 'Memory Management in Transformer Models', 'Maze-Solving Transformer Models', and some physics-related research like '“Myopic” Random Walk Problem', 'Neuromorphic Hardware Safety', 'Learning Quantum State Representations' etc.
Research Experience
Has research experience in machine learning and explainability; has been involved in projects such as Sparse Feature Circuits, LLM benchmark with board games, Automatic Circuit Discovery, Memory Management in Transformer Models, Maze-Solving Transformer Models, etc.
Background
A machine learning engineer focused on explainable AI.