SAEs Are Good for Steering -- If You Select the Right Features

Understand

Sparse Autoencoders (SAEs) have been proposed as an unsupervised approach to learn a decomposition of a model's latent space.

• This enables useful applications such as steering - influencing the output of a model towards a desired concept - without requiring labeled data.
• Current methods identify SAE features to steer by analyzing the input tokens that activate them.
• However, recent work has highlighted that activations alone do not fully describe the effect of a feature on the model's output.