Tag Title Year
ACL Knowledge neurons in pretrained transformers 2022
  On the pitfalls of analyzing individual neurons in language models 2022
  Discovering latent knowledge in language models without supervision. 2023
  What is one grain of sand in the desert? analyzing individual neurons in deep nlp models. 2018
EMNLP / Geva Transformer feed-forward layers are key-value memories. 2021
EMNLP / Geva Transformer feed-forward layers build predictions by promoting concepts in the vocabulary space. 2022
  Universal neurons in GPT2 language models. 2023
  Finding neurons in a haystack: Case studies with sparse probing. 2023