Pinned Loading

1. steering-bench steering-bench Public

   Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"

   Python 5 1

2. tms-kit tms-kit Public

   Toy models of superposition

   HTML 3

3. rl_cbf rl_cbf Public

   Code accompanying "Value Functions are Control Barrier Functions: Verification of Safe Policies using Control Theory"

   Python 22

4. openai-finetuner openai-finetuner Public

   High-level interface for launching and tracking OpenAI fine-tuning jobs

   Python

5. tiny-eval tiny-eval Public

   Python