Pinned Loading

1. sae-rm sae-rm Public

   Using SAE's to interpret Reward Models (RM)

   Jupyter Notebook 2 2

2. sparse_coding sparse_coding Public

   Forked from HoagyC/sparse_coding

   Jupyter Notebook 7 5

3. Optimal-Policies-Tend-To-Seek-Power Optimal-Policies-Tend-To-Seek-Power Public

   Code for the paper "Optimal Policies Tend To Seek Power"

   Mathematica 1

4. alignment-research-dataset alignment-research-dataset Public

   Forked from moirage/alignment-research-dataset

   A dataset of alignment research and code to reproduce it

   Python

5. STFT_wifi_physical_fingerprint STFT_wifi_physical_fingerprint Public

   Python 1

6. white-box white-box Public

   Forked from AlignmentResearch/tuned-lens

   Tools for understanding how transformer predictions are built layer-by-layer

   Jupyter Notebook