AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Authors: Zhengxuan Wu, Aryaman Arora, Atticus Geiger, Zheng Wang, Jing Huang, Dan Jurafsky, Christopher D. Manning, Christopher Potts

License: CC BY 4.0

Abstract: Fine-grained steering of language model outputs is essential for safety and reliability. Prompting and finetuning are widely used to achieve these goals, but interpretability researchers have proposed a variety of representation-based techniques as well, including sparse autoencoders (SAEs), linear artificial tomography, supervised steering vectors, linear probes, and representation finetuning. At present, there is no benchmark for making direct comparisons between these proposals. Therefore, we introduce AxBench, a large-scale benchmark for steering and concept detection, and report experiments on Gemma-2-2B and 9B. For steering, we find that prompting outperforms all existing methods, followed by finetuning. For concept detection, representation-based methods such as difference-in-means, perform the best. On both evaluations, SAEs are not competitive. We introduce a novel weakly-supervised representational method (Rank-1 Representation Finetuning; ReFT-r1), which is competitive on both tasks while providing the interpretability advantages that prompting lacks. Along with AxBench, we train and publicly release SAE-scale feature dictionaries for ReFT-r1 and DiffMean.

Submitted to arXiv on 28 Jan. 2025

Explore the paper tree

Click on the tree nodes to be redirected to a given paper and access their summaries and virtual assistant

Also access our AI generated Summaries, or ask questions about this paper to our AI assistant.

Look for similar papers (in beta version)

By clicking on the button above, our algorithm will scan all papers in our database to find the closest based on the contents of the full papers and not just on metadata. Please note that it only works for papers that we have generated summaries for and you can rerun it from time to time to get a more accurate result while our database grows.