Feature Rivalry in Sparse Autoencoder Representations: A Mechanistic Study of Uncertainty-Driven Feature Competition in LLMs
Paper • 2605.08149 • Published • 1
Harshavardhan NA
hvardhan878
AI & ML interests
None yet
Recent Activity
authored a paper about 16 hours ago
Self-Anchoring Calibration Drift in Large Language Models: How Multi-Turn Conversations Reshape Model Confidence authored a paper about 16 hours ago
Feature Rivalry in Sparse Autoencoder Representations: A Mechanistic Study of Uncertainty-Driven Feature Competition in LLMsOrganizations
None yet