Cite
Notes
Only stored in your browser.
Attribution
Opening the AI black box: program synthesis via mechanistic interpretability
arXiv 2024
Not All Language Model Features Are Linear
from 2 papers
Eric J. Michaud
Max Tegmark
professor
Anish Mudide
Chloe Loughridge
Joshua Engels
Mateja Vukelić
Tara Rezaei Kheirkhah
Vedang Lad
Wes Gurnee
Zifan Carl Guo