flâneur — a map of the web's best reading

interpreting GPT: the logit lens - AI Alignment Forum

alignmentforum.org · 5,358 words · saved by 1 readers

This post relates an observation I've made in my work with GPT-2, which I have not seen made elsewhere. …

x interpreting GPT: the logit lens — AI Alignment Forum GPT Machine Learning (ML) Gears-Level Interpretability (ML & AI) AI Frontpage 80 interpreting GPT: the logit lens by nostalgebraist 31st Aug 2020 13 min read 38 80 This post relates an observation I've made in my work with GPT-2, which I have not seen made elsewhere. IMO, this observation sheds a good deal of light on how the GPT-2/3/etc models (hereafter just "GPT") work internally. There is an accompanying Colab notebook which will let you interactively explore the phenomenon I describe here. [Edit: updated with another section on compa

Explore this link on the map →

related reading