Nora Belrose

Karma: 700

Estimating the Probability of Sampling a Trained Neural Network at Random

Adam Scherlis and Nora Belrose

1 Mar 2025 2:11 UTC

32 points

10 comments1 min readLW link

(arxiv.org)

Mechanistic Anomaly Detection Research Update

Nora Belrose and David Johnston

6 Aug 2024 10:33 UTC

11 points

0 comments1 min readLW link

(blog.eleuther.ai)

Open Source Automated Interpretability for Sparse Autoencoder Features

kh4dien, SrGonao, jacob_drori and Nora Belrose

30 Jul 2024 21:11 UTC

67 points

1 comment13 min readLW link

(blog.eleuther.ai)

Deconstructing Bostrom’s Classic Argument for AI Doom

Nora Belrose11 Mar 2024 5:58 UTC

16 points

14 comments1 min readLW link

(www.youtube.com)

Counting arguments provide no evidence for AI doom

Nora Belrose and Quintin Pope

27 Feb 2024 23:03 UTC

103 points

188 comments14 min readLW link

My Kind of Pragmatism

Nora Belrose20 May 2023 18:58 UTC

38 points

11 comments3 min readLW link

DeepMind’s generalist AI, Gato: A non-technical explainer

frances_lorenz, Nora Belrose and jonmenaster

16 May 2022 21:21 UTC

63 points

6 comments6 min readLW link