The Geometry of Categorical and Hierarchical Concepts in Large Language Models Paper • 2406.01506 • Published Jun 3 • 3
Extracting Latent Steering Vectors from Pretrained Language Models Paper • 2205.05124 • Published May 10, 2022
The Linear Representation Hypothesis and the Geometry of Large Language Models Paper • 2311.03658 • Published Nov 7, 2023 • 1