Nicholas Goldowsky-Dill
- Open Problems in Mechanistic Interpretability
2025/01/27 by Lee Sharkey, Sharkey, Lee, Bilal Chughtai +58 · 7 voices · 50 citations
Computer Science · #Natural Language Processing Techniques #Statistical and Computational Modeling #cs.LG
- Localizing Model Behavior with Path Patching
2023/04/12 by Nicholas Goldowsky-Dill, C. J. MacLeod, Goldowsky-Dill, Nicholas +5 · 23 citations
Computer Science · #Adversarial Robustness in Machine Learning #Explainable Artificial Intelligence (XAI) #Machine Learning in Healthcare
- Base-Axiom Initialization for Deliberative Alignment - A qualitative approach to Stress Testing Deliberative Alignment for Anti Scheming Training -
2025/09/19 by Bronson Schoen, Evgenia Nitishinskaya, Schoen, Bronson +37 · 10 voices · 13 citations
Computer Science · Engineering · #Software Engineering Techniques and Practices #Systems Engineering Methodologies and Applications #Teaching and Learning Programming #cs.AI
- Detecting Strategic Deception Using Linear Probes
2025/02/05 by Nicholas Goldowsky-Dill, Goldowsky-Dill, Nicholas, Bilal Chughtai +5 · 25 citations
Computer Science · Psychology · #Advanced Malware Detection Techniques #Deception detection and forensic psychology #FOS: Computer and information sciences #Machine Learning (cs.LG) #Network Security and Intrusion Detection
- Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
2024/05/17 by Dan Braun, Braun, Dan, Jordan Taylor +5 · 10 citations
Computer Science · #Natural Language Processing Techniques #Text and Document Classification Technologies #Video Analysis and Summarization
- Towards evaluations-based safety cases for AI scheming
2024/10/29 by Mikita Balesni, Marius Hobbhahn, Balesni, Mikita +29 · 8 citations
Engineering · Health Professions · Decision Sciences · #Safety Systems Engineering in Autonomy #Occupational Health and Safety Research #Risk and Safety Analysis
- The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks
2024/05/17 by Lucius Bushnaq, Stefan Heimersheim, Bushnaq, Lucius +17 · 2 citations
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications
- Using Degeneracy in the Loss Landscape for Mechanistic Interpretability
2024/05/17 by Lucius Bushnaq, Bushnaq, Lucius, Jake Mendel +13 · 1 citation
Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Statistical and Computational Modeling