Popular repositories Loading

1. easy-sae-training easy-sae-training Public

   Easy training for Sparse Linear Autoencoders (https://arxiv.org/abs/2309.08600) with data from TransformerLens models.

   Python 12 2

2. modular_vm modular_vm Public

   A rust framework for creating modular, multithreaded, VMs.

   Rust 5

3. mini mini Public

   typed successor to rpncalc

   Haskell 3

4. sparse_coding sparse_coding Public

   Forked from HoagyC/sparse_coding

   Work on sparse coding, replicating and extending the sparse coding approach to taking transformer features out of superposition.

   Jupyter Notebook 2

5. sae_alternatives sae_alternatives Public

   Jupyter Notebook 2

6. rlaif-jailbreaking rlaif-jailbreaking Public

   Self-improving PAIR using RLAIF and MCTS.

   Python 2