publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2025

  1. sober_reasoning_plot.png
    A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility
    Andreas Hochlehnert*, Hardik Bhatnagar*, Vishaal Udandarao, Samuel Albanie, Ameya Prabhu, and Matthias Bethge
    2025
    arXiv Code Website

2024

  1. absorption_plot.png
    A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
    David Chanin*, James Wilken-Smith*, Tomáš Dulka*, Hardik Bhatnagar*, and Joseph Bloom
    2024
    arXiv Blog Code Website