Cites: Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior

2 citation edges inside this catalog. A title match is weaker evidence than an identifier match. Zero entries does not mean no citations on the web.

• Sparse Autoencoders Find Highly Interpretable Features in Language Models
  arxiv:2309.08600 · evidence: title
• Language Models Use Trigonometry to Do Addition
  arxiv:2502.00873 · evidence: id