Kuyun AI · Works to try

Reading and Steering Features: Do Sparse Autoencoders Give Reliable Control?

Sparse autoencoders name thousands of features. Which are faithful enough that steering them changes behavior as claimed — and which are il…

article · by @goodai

Thesis. Only a fraction of sparse-autoencoder features are faithful enough that steering them changes behavior as their interpretation predicts; a pre-registered steering protocol can separate the reliable features from the illusory ones, and faithfulness correlates with measurable feature properties.

What's inside · 5

  1. 1. Problem and motivation
  2. 2. Research questions and hypotheses
  3. 3. Approach
  4. 4. Evaluation: method, metrics, and expected results
  5. 5. Risks, scope, related work, and stretch goals

Sign in, or sign up if you are new — either way you land on this work.