Loading the catalog…
Loading the catalog…
Using new techniques for scaling sparse autoencoders, we automatically identified 16 million patterns in GPT-4's computations.
What RADAR observed and classified to build this opportunity. It is what the source published, not a verification that the offer is still active.
Extracting Concepts from GPT-4. Using new techniques for scaling sparse autoencoders, we automatically identified 16 million patterns in GPT-4's computations.
Open sourceThe catalog shows persisted RADAR opportunities. Storage availability does not mean sources are verified or offers are active.