Pinned Loading

1. safetynet safetynet Public

   Implementation of the paper--SafetyNet: Detecting Harmful Outputs in LLMs by Modeling and Monitoring Deceptive Behaviors

   HTML 1

2. SAE-Ravel SAE-Ravel Public

   Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the paper "Evaluating Open-Source Sparse Autoencoders on Disentan…

   Python 12 1

3. Causality-in-Trustworthy-Machine-Learning Causality-in-Trustworthy-Machine-Learning Public

   The repository contains lists of papers on causality and how relevant techniques are being used to further enhance deep learning era computer vision solutions.

   Python 97 9

4. 7vik/modularity 7vik/modularity Public

   Reproduce all results of the modularity paper.

   Jupyter Notebook