Lignende værker

• The Linear Representation Hypothesis and the Geometry of Large Language Models
  af: Park, Kiho, et al.
  Udgivet: (2023)
• The Geometry of Categorical and Hierarchical Concepts in Large Language Models
  af: Park, Kiho, et al.
  Udgivet: (2024)
• Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures
  af: Muchane, Mark, et al.
  Udgivet: (2025)
• RATE: Causal Explainability of Reward Models with Imperfect Counterfactuals
  af: Reber, David, et al.
  Udgivet: (2024)
• Geometry-Lite: Interpretable Safety Probing via Layer-Wise Margin Geometry
  af: Sim, Woo Seob, et al.
  Udgivet: (2026)