Popular repositories Loading

1. claude-code-settings claude-code-settings Public

   Python 4

2. interpretable-fine-tuning interpretable-fine-tuning Public

   Training components that act on SAE latents so that it is describe what was learned during fine-tuning

   Jupyter Notebook 2

3. openrouter_reliable_research_search openrouter_reliable_research_search Public

   Do researchers use OpenRouter reliably? Best practices, a survey of public research code, taxonomy of mistakes, and a Claude skill.

   HTML 2

4. OrbitGame OrbitGame Public

   CircleOrbitMouse.java has the main method

   Java 1

5. sae_jailbreak_unlearning sae_jailbreak_unlearning Public

   Investigating how well intervening on Sparse Autoencoder internals prevents adversaries from accessing dangerous knowledge.

   Jupyter Notebook 1

6. SWE-bench SWE-bench Public

   Forked from SWE-bench/SWE-bench

   SWE-bench [Multimodal]: Can Language Models Resolve Real-world Github Issues? \n AMindToThink added newer models to inference including DeepSeek and 4o mini

   Python 1