OpenAI ↗ · 2024-06-06 08:00 · UTC+8
Extracting Concepts from GPT-4
Company news OpenAI Source language: English
Using new techniques for scaling sparse autoencoders, we automatically identified 16 million patterns in GPT-4's computations.
Excerpt
Using new techniques for scaling sparse autoencoders, we automatically identified 16 million patterns in GPT-4's computations.
Short excerpt from the source — open the original for the full text.