Cite
Notes
Only stored in your browser.
Attribution
A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility
arXiv 2025
A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
arXiv 2024
from 2 papers
Ameya Prabhu
Andreas Hochlehnert
David Chanin
James Wilken-Smith
Joseph Bloom
Matthias Bethge
Samuel Albanie
Tomáš Dulka
Vishaal Udandarao