Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks

Documenti analoghi

• SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
  di: Karvonen, Adam, et al.
  Pubblicazione: (2025)
• Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
  di: Casademunt, Helena, et al.
  Pubblicazione: (2025)
• Robustly Improving LLM Fairness in Realistic Settings via Interpretability
  di: Karvonen, Adam, et al.
  Pubblicazione: (2025)
• Learning Multi-Level Features with Matryoshka Sparse Autoencoders
  di: Bussmann, Bart, et al.
  Pubblicazione: (2025)
• Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
  di: Marks, Samuel, et al.
  Pubblicazione: (2024)