Nora Belrose

According to our database, Nora Belrose authored at least 19 papers between 2022 and 2025.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2025

Examining Two Hop Reasoning Through Information Content Scaling.

David Johnston, Nora Belrose

CoRR, February, 2025

Slowing Learning by Erasing Simple Features.

Lucia Quirke, Nora Belrose

CoRR, February, 2025

Converting MLPs into Polynomials in Closed Form.

Nora Belrose, Alice Rigg

CoRR, February, 2025

Partially Rewriting a Transformer in Natural Language.

Gonçalo Paulo, Nora Belrose

CoRR, January, 2025

Transcoders Beat Sparse Autoencoders for Interpretability.

Gonçalo Paulo, Stepan Shabalin, Nora Belrose

CoRR, January, 2025

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

Adam Scherlis, Nora Belrose

CoRR, January, 2025

Sparse Autoencoders Trained on the Same Data Learn Different Features.

Gonçalo Paulo, Nora Belrose

CoRR, January, 2025

2024

Understanding Gradient Descent through the Training Jacobian.

Nora Belrose, Adam Scherlis

CoRR, 2024

Refusal in LLMs is an Affine Function.

Thomas Marshall, Adam Scherlis, Nora Belrose

CoRR, 2024

Automatically Interpreting Millions of Features in Large Language Models.

Gonçalo Paulo, Alex Mallen, Caden Juang, Nora Belrose

CoRR, 2024

Balancing Label Quantity and Quality for Scalable Elicitation.

Alex Mallen, Nora Belrose

CoRR, 2024

Does Transformer Interpretability Transfer to RNNs?

Gonçalo Paulo, Thomas Marshall, Nora Belrose

CoRR, 2024

Neural Networks Learn Statistics of Increasing Complexity.

Nora Belrose, Quintin Pope, Lucia Quirke, Alex Mallen, Xiaoli Z. Fern

Proceedings of the Forty-first International Conference on Machine Learning, 2024

2023

Eliciting Latent Knowledge from Quirky Language Models.

Alex Mallen, Nora Belrose

CoRR, 2023

Eliciting Latent Predictions from Transformers with the Tuned Lens.

Nora Belrose, Zach Furman, Logan Smith, Danny Halawi, Igor Ostrovsky, Lev McKinney, Stella Biderman, Jacob Steinhardt

CoRR, 2023

LEACE: Perfect linear concept erasure in closed form.

Nora Belrose, David Schneider-Joseph, Shauli Ravfogel, Ryan Cotterell, Edward Raff, Stella Biderman

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Adversarial Policies Beat Superhuman Go AIs.

Tony Tong Wang, Adam Gleave, Tom Tseng, Kellin Pelrine, Nora Belrose, Joseph Miller, Michael D. Dennis, Yawen Duan, Viktor Pogrebniak, Sergey Levine, Stuart Russell

Proceedings of the International Conference on Machine Learning, 2023

2022

imitation: Clean Imitation Learning Implementations.

Adam Gleave, Mohammad Taufeeque, Juan Rocamonde, Erik Jenner, Steven H. Wang, Sam Toyer, Maximilian Ernestus, Nora Belrose, Scott Emmons, Stuart Russell

CoRR, 2022

Adversarial Policies Beat Professional-Level Go AIs.

Tony Tong Wang, Adam Gleave, Nora Belrose, Tom Tseng, Joseph Miller, Michael D. Dennis, Yawen Duan, Viktor Pogrebniak, Sergey Levine, Stuart Russell

CoRR, 2022