Google Colab (Monosemanticity / Pythia Practice)
Google Colab (Sparse Autoencoders replication from Neel)
Google Colab (PPO)
Google Colab (Fine-tuning)
Google Colab (Analysis of fine-tuning)
Stephen Casper, Tony Wang, Eric Michaud (10/16/2023)
Logan Meeting (10/20/2023)
Relevant papers
Wednesday, 10/25/2023
Thursday, 10/26/2023
Friday, 10/27/2023
Saturday, 10/28/2023
Sunday, 11/26/2023
Sunday, 12/3/2023
SAE feature descriptions!
Tuesday, 12/5