Nora Belrose
- Adversarial Policies Beat Superhuman Go AIs
2022/11/01 by Tony Tong Wang, Tony T. Wang, Adam Gleave +21 · 18 voices · 10 citations
Computer Science · Social Sciences · #Adversarial Robustness in Machine Learning #Advanced Malware Detection Techniques #Ethics and Social Impacts of AI
- Eliciting Latent Predictions from Transformers with the Tuned Lens
2023/03/14 by Nora Belrose, Igor Ostrovsky, Belrose, Nora +13 · 3 voices · 70 citations
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.LG
- LEACE: Perfect linear concept erasure in closed form
2023/06/06 by Nora Belrose, Belrose, Nora, David Schneider-Joseph +9 · 1 voice · 40 citations
Computer Science · Social Sciences · #Machine Learning in Healthcare #Misinformation and Its Impacts #Topic Modeling #cs.CL #cs.CY #cs.LG
- Automatically Interpreting Millions of Features in Large Language Models
2024/10/17 by Gonçalo Paulo, Paulo, Gonçalo, Alex Mallen +6 · 1 voice · 39 citations
Computer Science · #Natural Language Processing Techniques #Topic Modeling
- Sparse Autoencoders Trained on the Same Data Learn Different Features
2025/01/28 by Gonçalo Paulo, Nora Belrose, Paulo, Gonçalo +1 · 25 citations
Computer Science · #Machine Learning and Data Classification
- imitation: Clean Imitation Learning Implementations
2022/11/22 by Adam Gleave, Mohammad Taufeeque, Gleave, Adam +17 · 8 citations
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Reinforcement Learning in Robotics #Robot Manipulation and Learning #Robotic Locomotion and Control
- Neural Networks Learn Statistics of Increasing Complexity
2024/02/06 by Nora Belrose, Belrose, Nora, Quintin Pope +7 · 9 citations
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications
- Does Transformer Interpretability Transfer to RNNs?
2024/04/09 by Gonçalo Paulo, Paulo, Gonçalo, Thomas Marshall +3 · 1 voice · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #cs.AI #cs.CL #cs.LG
- Refusal in LLMs is an Affine Function
2024/11/13 by Thomas Marshall, Thomas Märshall, Adam Scherlis +4 · 1 voice · 4 citations
Computer Science · #Multi-Agent Systems and Negotiation #cs.CL #cs.LG
- Understanding Gradient Descent through the Training Jacobian
2024/12/09 by Nora Belrose, Adam Scherlis, Belrose, Nora +1 · 2 voices · 1 citation
#cs.LG
- Balancing Label Quantity and Quality for Scalable Elicitation
2024/10/17 by Alex Mallen, Nora Belrose, Mallen, Alex +1 · 1 citation
Pharmacology, Toxicology and Pharmaceutics · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Pharmacy and Medical Practices