{"total":88,"rows":[{"id":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316,"area":null},{"id":"2305.00586","title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model","created":"2023-04-30","cited_by_count":202,"area":null},{"id":"2304.05969","title":"Localizing Model Behavior with Path Patching","created":"2023-04-12","cited_by_count":195,"area":null},{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","cited_by_count":131,"area":null},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126,"area":null},{"id":"2310.19775","title":"Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions","created":"2023-10-30","cited_by_count":125,"area":null},{"id":"2310.17191","title":"How do Language Models Bind Entities in Context?","created":"2023-10-26","cited_by_count":108,"area":null},{"id":"2301.05062","title":"Tracr: Compiled Transformers as a Laboratory for Interpretability","created":"2023-01-12","cited_by_count":104,"area":null},{"id":"2311.02462","title":"Levels of AGI for Operationalizing Progress on the Path to AGI","created":"2023-11-04","cited_by_count":96,"area":null},{"id":"2405.00208","title":"A Primer on the Inner Workings of Transformer-based Language Models","created":"2024-04-30","cited_by_count":85,"area":null},{"id":"2310.04625","title":"Copy Suppression: Comprehensively Understanding an Attention Head","created":"2023-10-06","cited_by_count":76,"area":null},{"id":"2310.10616","title":"How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations","created":"2023-10-16","cited_by_count":75,"area":null},{"id":"2409.03752","title":"Attention Heads of Large Language Models: A Survey","created":"2024-09-05","cited_by_count":67,"area":null},{"id":"2404.00806","title":"Algorithmic Collusion by Large Language Models","created":"2024-03-31","cited_by_count":62,"area":null},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2409.00265","title":"Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction","created":"2024-08-30","cited_by_count":46,"area":null},{"id":"2404.08978","title":"Incremental Residual Concept Bottleneck Models","created":"2024-04-13","cited_by_count":43,"area":null},{"id":"2410.02984","title":"Differentiation and Specialization of Attention Heads via the Refined Local Learning Coefficient","created":"2024-10-03","cited_by_count":40,"area":null},{"id":"2407.16711","title":"Benchmarks as Microscopes: A Call for Model Metrology","created":"2024-07-22","cited_by_count":35,"area":null},{"id":"2307.03637","title":"Discovering Variable Binding Circuitry with Desiderata","created":"2023-07-07","cited_by_count":34,"area":null},{"id":"2310.13121","title":"Understanding Addition in Transformers","created":"2023-10-19","cited_by_count":34,"area":null},{"id":"2309.10498","title":"A Configurable Library for Generating and Manipulating Maze Datasets","created":"2023-09-19","cited_by_count":31,"area":null},{"id":"2309.05973","title":"Circuit Breaking: Removing Model Behaviors with Targeted Ablation","created":"2023-09-12","cited_by_count":27,"area":null},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2312.08550","title":"Harmonics of Learning: Universal Fourier Features Emerge in Invariant Networks","created":"2023-12-13","cited_by_count":23,"area":null},{"id":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2409.13456","title":"Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?","created":"2024-09-20","cited_by_count":18,"area":null},{"id":"2309.08395","title":"Learning by Self-Explaining","created":"2023-09-15","cited_by_count":17,"area":null},{"id":"2310.04475","title":"Demystifying Embedding Spaces using Large Language Models","created":"2023-10-06","cited_by_count":17,"area":null},{"id":"2401.17975","title":"Understanding polysemanticity in neural networks through coding theory","created":"2024-01-31","cited_by_count":17,"area":null},{"id":"2312.02566","title":"Structured World Representations in Maze-Solving Transformers","created":"2023-12-05","cited_by_count":16,"area":null},{"id":"2502.11019","title":"Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning","created":"2025-02-16","cited_by_count":16,"area":null},{"id":"2406.00053","title":"Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting","created":"2024-05-28","cited_by_count":15,"area":null},{"id":"2411.06090","title":"Concept Bottleneck Language Models For protein design","created":"2024-11-09","cited_by_count":15,"area":null},{"id":"2304.06715","title":"Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2404.18191","title":"Exploring the Robustness of In-Context Learning with Noisy Labels","created":"2024-04-28","cited_by_count":14,"area":null},{"id":"2310.11884","title":"From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networks","created":"2023-10-18","cited_by_count":13,"area":null},{"id":"2308.01154","title":"Arithmetic with Language Models: from Memorization to Computation","created":"2023-08-02","cited_by_count":12,"area":null},{"id":"2312.12747","title":"ALMANACS: A Simulatability Benchmark for Language Model Explainability","created":"2023-12-20","cited_by_count":11,"area":null},{"id":"2310.06253","title":"A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning","created":"2023-10-10","cited_by_count":9,"area":null},{"id":"2311.13186","title":"Applications of Spiking Neural Networks in Visual Place Recognition","created":"2023-11-22","cited_by_count":9,"area":null},{"id":"2306.02149","title":"A General Framework for Interpretable Neural Learning based on Local Information-Theoretic Goal Functions","created":"2023-06-03","cited_by_count":8,"area":null},{"id":"2306.07397","title":"Adversarial Attacks on the Interpretation of Neuron Activation Maximization","created":"2023-06-12","cited_by_count":7,"area":null},{"id":"2311.00863","title":"Training Dynamics of Contextual N-Grams in Language Models","created":"2023-11-01","cited_by_count":7,"area":null},{"id":"2405.17088","title":"Phase Transitions in the Output Distribution of Large Language Models","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2410.03020","title":"On Logical Extrapolation for Mazes with Recurrent and Implicit Networks","created":"2024-10-03","cited_by_count":7,"area":null},{"id":"2211.10024","title":"Diagnostics for Deep Neural Networks with Automated Copy/Paste Attacks","created":"2022-11-18","cited_by_count":6,"area":null},{"id":"2408.12664","title":"Multilevel Interpretability Of Artificial Neural Networks: Leveraging Framework And Methods From Neuroscience","created":"2024-08-22","cited_by_count":5,"area":null},{"id":"2409.13684","title":"The FIX Benchmark: Extracting Features Interpretable to eXperts","created":"2024-09-20","cited_by_count":5,"area":null},{"id":"2411.02461","title":"Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2505.16705","title":"An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations","created":"2025-05-22","cited_by_count":5,"area":null},{"id":"2404.08964","title":"Understanding Multimodal Deep Neural Networks: A Concept Selection View","created":"2024-04-13","cited_by_count":4,"area":null},{"id":"2605.05076","title":"High-Dimensional Statistics: Reflections on Progress and Open Problems","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2309.10209","title":"Towards Effective Semantic OOD Detection in Unseen Domains: A Domain Generalization Perspective","created":"2023-09-18","cited_by_count":3,"area":null},{"id":"2402.08211","title":"Transformer Mechanisms Mimic Frontostriatal Gating Operations When Trained on Human Working Memory Tasks","created":"2024-02-13","cited_by_count":3,"area":null},{"id":"2404.02949","title":"The SaTML '24 CNN Interpretability Competition: New Innovations for Concept-Level Interpretability","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2407.10543","title":"Understanding the Dependence of Perception Model Competency on Regions in an Image","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2505.13899","title":"Causes and Consequences of Representational Similarity in Machine Learning Models","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2607.22367","title":"Interior interpretability with attention rollout: contraction and propagation profiles in Transformers","created":"2026-07-24","cited_by_count":3,"area":null},{"id":"2302.09071","title":"Rejecting Cognitivism: Computational Phenomenology for Deep Learning","created":"2023-02-16","cited_by_count":2,"area":null},{"id":"2303.01739","title":"Study of Distractors in Neural Models of Code","created":"2023-03-03","cited_by_count":2,"area":null},{"id":"2303.15201","title":"Learning An Active Inference Model of Driver Perception and Control: Application to Vehicle Car-Following","created":"2023-03-27","cited_by_count":2,"area":null},{"id":"2306.12609","title":"Towards Regulatable AI Systems: Technical Gaps and Policy Opportunities","created":"2023-06-22","cited_by_count":2,"area":null},{"id":"2406.02060","title":"I've got the \"Answer\"! Interpretation of LLMs Hidden States in Question Answering","created":"2024-06-04","cited_by_count":2,"area":null},{"id":"2410.18541","title":"On Explaining with Attention Matrices","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2507.00163","title":"Prompting as Scientific Inquiry","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2306.02979","title":"The Chai Platform's AI Safety Framework","created":"2023-06-05","cited_by_count":1,"area":null},{"id":"2407.08934","title":"Compositional Structures in Neural Embedding and Interaction Decompositions","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2410.07962","title":"Towards Assurance of LLM Adversarial Robustness using Ontology-Driven Argumentation","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2501.00528","title":"PyMilo: A Python Library for ML I/O","created":"2024-12-31","cited_by_count":1,"area":null},{"id":"2511.01096","title":"Hyper Hawkes Processes: Interpretable Models of Marked Temporal Point Processes","created":"2025-11-02","cited_by_count":1,"area":null},{"id":"2603.02200","title":"Adaptive Confidence Regularization for Multimodal Failure Detection","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2603.27868","title":"A Revealed Preference Framework for AI Alignment","created":"2026-03-29","cited_by_count":1,"area":null},{"id":"2212.06576","title":"AI Model Utilization Measurements For Finding Class Encoding Patterns","created":"2022-12-12","cited_by_count":0,"area":null},{"id":"2310.02430","title":"Episodic Memory Theory for the Mechanistic Interpretation of Recurrent Neural Networks","created":"2023-10-03","cited_by_count":0,"area":null},{"id":"2409.16865","title":"Linking in Style: Understanding learned features in deep learning models","created":"2024-09-25","cited_by_count":0,"area":null},{"id":"2411.18645","title":"Bi-ICE: An Inner Interpretable Framework for Image Classification via Bi-directional Interactions between Concept and Input Embeddings","created":"2024-11-26","cited_by_count":0,"area":null},{"id":"2412.10538","title":"Predictive Modeling, Pattern Recognition, and Spatiotemporal Representations of Plant Growth in Simulated and Controlled Environments: A Comprehensive Review","created":"2024-12-13","cited_by_count":0,"area":null},{"id":"2412.15698","title":"Concept Boundary Vectors","created":"2024-12-20","cited_by_count":0,"area":null},{"id":"2504.05254","title":"Explaining Low Perception Model Competency with High-Competency Counterfactuals","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2505.02859","title":"Enhancing ML Model Interpretability: Leveraging Fine-Tuned Large Language Models for Better Understanding of AI","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2505.15570","title":"Out-of-Distribution Detection via Channelwise Feature Aggregation in Neural Network-Based Receivers","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2506.15541","title":"Intrinsic and Extrinsic Organized Attention: Softmax Invariance and Network Sparsity","created":"2025-06-18","cited_by_count":0,"area":null},{"id":"2507.18681","title":"Concept Probing: Where to Find Human-Defined Concepts (Extended Version)","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2604.00324","title":"The Persistent Vulnerability of Aligned AI Systems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.18801","title":"Position: Let's Develop Data Probes to Fundamentally Understand How Data Affects LLM Performance","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2607.07127","title":"Weight-Space Physics: Interpretable Hypernetworks for Lattice Quantum Field Theories","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2609.22249","title":"A Tutorial on Prompt Engineering: From Messy Thoughts to AI Workflows","created":"2026-09-05","cited_by_count":0,"area":null}],"next_cursor":null}