Texonom AI

AI & ML interests

NLP, Taxonomy

Recent Activity

seonglae  authored a paper 1 day ago

The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models

seonglae  authored a paper 7 months ago

CorrSteer: Steering Improves Task Performance and Safety in LLMs through Correlation-based Sparse Autoencoder Feature Selection

seonglae  authored a paper 8 months ago

FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies

View all activity

Team members 1