AI brief
A LessWrong post reports that Opus 5.5 can identify 3-19% of GPT 2-XL's neurons from their activations, compared with 0.3% that GPT-4 achieved in 2023.
Written by AI from LessWrong's published text.
Source
“In which I investigate if Opus is able to interpret neurons better than GPT 4. TLDR: Opus 5.5 is able to identify 3-19% of the neurons of GPT 2-XL based on activations. This is a big improvement over the 0.3% that GPT-4 was able to achieve in 2023.”
Interpretation or community commentary rather than straight reporting.
Read original story ↗