Lars Kai Hansen
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper demonstrates that Sparse Autoencoders (SAEs) can effectively steer Large Language Models (LLMs) on the AxBench benchmark, achieving performance comparable to LoRA baselines when combined with a novel supervised feature selection pipeline.
This paper demonstrates that Sparse Autoencoders (SAEs) can effectively steer Large Language Models (LLMs) on the AxBench benchmark, achieving performance comparable to LoRA baselines when combined with a novel supervised feature selection pipeline.
Papers
Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines
This paper demonstrates that Sparse Autoencoders (SAEs) can effectively steer Large Language Models (LLMs) on the AxBench benchmark, achieving performance comparable to LoRA baselines when combined wi…