3 papers
cs.LG2026
The Information Geometry of Softmax: Probing and Steering
Kiho Park, Todd Nief, Yo Joong Choe +1
This paper concerns the question of how AI systems encode semantic structure into the geometric structure of their representation spaces. The motivating observation is that the nat…
cs.CL2025
Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures
Mark Muchane, Sean Richardson, Kiho Park +1
Sparse dictionary learning (and, in particular, sparse autoencoders) attempts to learn a set of human-understandable concepts that can explain variation on an abstract space. A bas…
cs.CL2025
The Geometry of Categorical and Hierarchical Concepts in Large Language Models
Kiho Park, Yo Joong Choe, Yibo Jiang +1
The linear representation hypothesis is the informal idea that semantic concepts are encoded as linear directions in the representation spaces of large language models (LLMs). Prev…