Cite
Notes
Only stored in your browser.
Attribution
Parameterized Synthetic Text Generation with SimpleStories
arXiv 2025
Refusal in LLMs is an Affine Function
arXiv 2024
Does Transformer Interpretability Transfer to RNNs?
from 3 papers
Nora Belrose
Adam Scherlis
Chandan Sreedhara
Dan Braun
Emerald Zhang
Gonçalo Paulo
Juan Diego Rodriguez
Lennart Finke
Mat Allen
Noa Nabeshima