conftrace_

rank-1 representation finetuning

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

reft-r1 (1) difference-in-means (1) prompting (1) fine tuning (1) sparse autoencoder (1)

Papers

AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders ICML 2025