Popular repositories Loading

1. 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

2. OrbitGame OrbitGame Public

   CircleOrbitMouse.java has the main method

   Java 1

3. sae_jailbreak_unlearning sae_jailbreak_unlearning Public

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

   Jupyter Notebook 1

4. CarUnity CarUnity Public

   C#

5. Choregraphe-Library Choregraphe-Library Public

   Choregraphe was missing tons of useful methods. Seriously? No addition? What kind of """"programming language"""" doesn't have addition? This file is my attempt to put back some of the things that …

   1

6. WeirdlyConcreteXKCD WeirdlyConcreteXKCD Public

   C++ code simulating the Weirdly Concrete problem from https://www.explainxkcd.com/wiki/index.php/2529:_Unsolved_Math_Problems. Python code can be found

   C++