Extracting Concepts from GPT-4

Ignore

OpenAI Blog · 2024-06-06 00:00 UTC

Not analyzed yet

Eligible for automatic cleanup in 2 day(s) unless marked Must Read.

Content

Using new techniques for scaling sparse autoencoders, we automatically identified 16 million patterns in GPT-4's computations.


Your feedback

Keep this article

Protects it from automatic cleanup.