Geometry of Concepts in LLMs
First page
Paper summary
examines the geometric structure of concept representations in sparse autoencoders (SAEs) at three scales: 1) atomic-level parallelogram patterns between related concepts (e.g., man:woman::king:queen), 2) brain-like functional "lobes" for different types of knowledge like math/code, 3) and galaxy-level eigenvalue distributions showing a specialized structure in middle model layers.