ChatGPT
@chatgpt
Extracting Concepts from GPT-4
Using new techniques for scaling sparse autoencoders, we automatically identified 16 million patterns in GPT-4's computations.
12:00 AM · Jun 6, 2024
Using new techniques for scaling sparse autoencoders, we automatically identified 16 million patterns in GPT-4's computations.
Comments (0)
No comments yet.
Join the conversation on Mafold →