Co-occurring keywords · papers mentioning both
Papers
How Many Features Can a Language Model Store Under the Linear Representation Hypothesis?
COLT 2026
FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering
ACL 2025
The Geometry of Categorical and Hierarchical Concepts in Large Language Models
ICLR 2025
The Logical Implication Steering Method for Conditional Interventions on Transformer Generation
ICML 2025
Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations
EMNLP 2024
The Linear Representation Hypothesis and the Geometry of Large Language Models
ICML 2024