Charles O’Neill

1. Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models
   2024/05/21 by Charles O’Neill, Thang Bui, O'Neill, Charles +1 · 4 citations
   Computer Science · Materials Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Machine Learning in Materials Science #Natural Language Processing Techniques
2. Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders
   2024/11/20 by Charles O'Neill, Charles O’Neill, O'Neill, Charles +4 · 1 voice · 5 citations
   Computer Science · #Generative Adversarial Networks and Image Synthesis #Neural Networks and Applications #cs.LG
3. From superposition to sparse codes: interpretable representations in neural networks
   2025/03/03 by David Klindt, Charles O’Neill, Charles O'Neill +8 · 1 voice · 5 citations
   Computer Science · #Neural Networks and Applications #cs.LG
4. Grokking Beyond Neural Networks: An Empirical Exploration with Model Complexity
   2023/10/26 by Jack Miller, Miller, Jack, Charles O’Neill +3 · 3 citations
   Computer Science · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Neural Networks and Applications
5. Adversarial Fine-Tuning of Language Models: An Iterative Optimisation Approach for the Generation and Detection of Problematic Content
   2023/08/26 by Charles O’Neill, O'Neill, Charles, Jack Miller +7 · 2 citations
   Computer Science · #Adversarial Robustness in Machine Learning #Hate Speech and Cyberbullying Detection #Topic Modeling
6. Disentangling Dense Embeddings with Sparse Autoencoders
   2024/08/01 by Charles O’Neill, Christine Ye, O'Neill, Charles +5 · 3 citations
   Computer Science · #Digital Media Forensic Detection #Generative Adversarial Networks and Image Synthesis #Adversarial Robustness in Machine Learning
7. Sparks of Science: Hypothesis Generation Using Structured Paper Data
   2025/04/17 by Charles O’Neill, Tirthankar Ghosal, O'Neill, Charles +11 · 3 citations
   Computer Science · Materials Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning in Materials Science #Multimodal Machine Learning Applications #Topic Modeling
8. Eigenvalue initialisation and regularisation for Koopman autoencoders
   2022/12/23 by Jack Miller, Miller, Jack W., Charles O’Neill +5 · 1 citation
   Physics and Astronomy · Computer Science · Engineering · #Model Reduction and Neural Networks #Generative Adversarial Networks and Image Synthesis #Energy Load and Power Forecasting
9. A Single Direction of Truth: An Observer Model's Linear Residual Probe Exposes and Steers Contextual Hallucinations
   2025/07/31 by Charles O’Neill, Slava Chalnev, O'Neill, Charles +6 · 4 citations
   Psychology · Neuroscience · #Mental Health Research Topics #Functional Brain Connectivity Studies #Paranormal Experiences and Beliefs
10. A unifying framework from neural superposition to sparse interpretable codes
    2026/07/14 by David Klindt, Charles O’Neill, Patrik Reizinger +2 · 2 voices
    Neuroscience · Computer Science · #Face Recognition and Perception #Explainable Artificial Intelligence (XAI) #Embodied and Extended Cognition