LessWrong (30+ Karma)

“Is GPT 2XL already clean?” by Jasper Blank

12:26

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.

#AI notice: This post is human written but in the research there was heavy use of Opus 5.5. I mainly asked it to rerun this 2023 paper to see how…