{"total":104,"rows":[{"id":"2408.10205","title":"KAN 2.0: Kolmogorov-Arnold Networks Meet Science","created":"2024-08-19","cited_by_count":118,"area":null},{"id":"2405.15943","title":"Transformers represent belief state geometry in their residual stream","created":"2024-05-24","cited_by_count":77,"area":null},{"id":"2601.04480","title":"When Models Manipulate Manifolds: The Geometry of a Counting Task","created":"2026-01-08","cited_by_count":46,"area":null},{"id":"2507.01786","title":"Probing and Steering Evaluation Awareness of Language Models","created":"2025-07-02","cited_by_count":35,"area":null},{"id":"2410.11781","title":"Language Models Encode Numbers Using Digit Representations in Base 10","created":"2024-10-15","cited_by_count":32,"area":null},{"id":"2410.21869","title":"Cross-Entropy Is All You Need To Invert the Data Generating Process","created":"2024-10-29","cited_by_count":31,"area":null},{"id":"2604.21691","title":"There Will Be a Scientific Theory of Deep Learning","created":"2026-04-23","cited_by_count":29,"area":null},{"id":"2409.05448","title":"Representational Analysis of Binding in Language Models","created":"2024-09-09","cited_by_count":28,"area":null},{"id":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2407.14662","title":"Relational Composition in Neural Networks: A Survey and Call to Action","created":"2024-07-19","cited_by_count":23,"area":null},{"id":"2602.07488","title":"Deriving Neural Scaling Laws from the statistics of natural language","created":"2026-02-07","cited_by_count":23,"area":null},{"id":"2406.10777","title":"RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning","created":"2024-06-16","cited_by_count":21,"area":null},{"id":"2410.08113","title":"Robust AI-Generated Text Detection by Restricted Embeddings","created":"2024-10-10","cited_by_count":18,"area":null},{"id":"2507.12379","title":"Probing for Arithmetic Errors in Language Models","created":"2025-07-16","cited_by_count":18,"area":null},{"id":"2410.01444","title":"Geometric Signatures of Compositionality Across a Language Model's Lifetime","created":"2024-10-02","cited_by_count":16,"area":null},{"id":"2502.01954","title":"Constrained belief updates explain geometric structures in transformer representations","created":"2025-02-04","cited_by_count":15,"area":null},{"id":"2410.11042","title":"Persistent Topological Features in Large Language Models","created":"2024-10-14","cited_by_count":12,"area":null},{"id":"2602.02464","title":"From Directions to Regions: Decomposing Activations in Language Models via Local Geometry","created":"2026-02-02","cited_by_count":12,"area":null},{"id":"2602.11246","title":"How Many Features Can a Language Model Store Under the Linear Representation Hypothesis?","created":"2026-02-11","cited_by_count":12,"area":null},{"id":"2505.11770","title":"Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors","created":"2025-05-17","cited_by_count":11,"area":null},{"id":"2508.11214","title":"How Causal Abstraction Underpins Computational Explanation","created":"2025-08-15","cited_by_count":11,"area":null},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"id":"2605.01148","title":"Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts","created":"2026-05-01","cited_by_count":10,"area":null},{"id":"2505.05145","title":"Understanding In-context Learning of Addition via Activation Subspaces","created":"2025-05-08","cited_by_count":8,"area":null},{"id":"2507.23220","title":"Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders","created":"2025-07-31","cited_by_count":8,"area":null},{"id":"2510.01025","title":"Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2602.16698","title":"Causality is Key for Interpretability Claims to Generalise","created":"2026-02-18","cited_by_count":8,"area":null},{"id":"2405.17420","title":"Survival of the Fittest Representation: A Case Study with Modular Addition","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2512.15134","title":"From Isolation to Entanglement: When Do Interpretability Methods Identify and Disentangle Known Concepts?","created":"2025-12-17","cited_by_count":7,"area":null},{"id":"2602.02385","title":"Transformers learn factored representations","created":"2026-02-02","cited_by_count":7,"area":null},{"id":"2407.11542","title":"Counting in Small Transformers: The Delicate Interplay between Attention and Feed-Forward Layers","created":"2024-07-16","cited_by_count":6,"area":null},{"id":"2604.20817","title":"Convergent Evolution: How Different Language Models Learn Similar Number Representations","created":"2026-04-22","cited_by_count":6,"area":null},{"id":"2506.03790","title":"Attention-Only Transformers via Unrolled Subspace Denoising","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2605.01844","title":"The Cylindrical Representation Hypothesis for Language Model Steering","created":"2026-05-03","cited_by_count":5,"area":null},{"id":"2606.25234","title":"Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2508.00331","title":"Embryology of a Language Model","created":"2025-08-01","cited_by_count":4,"area":null},{"id":"2509.06938","title":"From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers","created":"2025-09-08","cited_by_count":4,"area":null},{"id":"2509.19372","title":"Representation-based Broad Hallucination Detectors Fail to Generalize Out of Distribution","created":"2025-09-19","cited_by_count":4,"area":null},{"id":"2511.21594","title":"Visualizing LLM Latent Space Geometry Through Dimensionality Reduction","created":"2025-11-26","cited_by_count":4,"area":null},{"id":"2602.02224","title":"Spectral Superposition: A Theory of Feature Geometry","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2505.18575","title":"Response Uncertainty and Probe Modeling: Two Sides of the Same Coin in LLM Interpretability?","created":"2025-05-24","cited_by_count":3,"area":null},{"id":"2510.06700","title":"How Language Models Conflate Logical Validity with Plausibility: A Representational Analysis of Content Effects","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2511.16309","title":"Sparse Autoencoders are Topic Models","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2602.04752","title":"Decomposing Query-Key Feature Interactions Using Contrastive Covariances","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2602.05184","title":"Towards Worst-Case Guarantees with Scale-Aware Interpretability","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2603.01227","title":"The Lattice Representation Hypothesis of Large Language Models","created":"2026-03-01","cited_by_count":3,"area":null},{"id":"2606.09658","title":"Muon Learns More Robust and Transferable Features than Adam","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2510.26285","title":"Language Models Learn Universal Representations of Numbers and Here's Why You Should Care","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2604.10158","title":"Tracing the Thought of a Grandmaster-level Chess-Playing Transformer","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2607.04525","title":"Language Models Represent and Transform Concepts with Shared Geometry","created":"2026-07-05","cited_by_count":2,"area":null},{"id":"2608.27540","title":"Towards a mathematical theory of superposition","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2505.11576","title":"Concept-Guided Interpretability via Neural Chunking","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2505.16178","title":"Understanding Fact Recall in Language Models: Why Two-Stage Training Encourages Memorization but Mixed Training Teaches Knowledge","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2508.02527","title":"I Have No Mouth, and I Must Rhyme: Uncovering Internal Phonetic Representations in LLaMA 3.2","created":"2025-08-04","cited_by_count":1,"area":null},{"id":"2509.21993","title":"Bilinear representation mitigates reversal curse and enables consistent model editing","created":"2025-09-26","cited_by_count":1,"area":null},{"id":"2602.14490","title":"Parameter-Efficient Fine-Tuning of LLMs with Mixture of Space Experts","created":"2026-02-16","cited_by_count":1,"area":null},{"id":"2603.23821","title":"Perturbation: A simple and efficient adversarial tracer for representation learning in language models","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2605.23821","title":"Hierarchical Concept Geometry in Language Models Emerges from Word Co-occurrence","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2605.24942","title":"Riemannian-Manifold Steering: Geometry-Aware Generative Autoencoders for Label-Free Steering","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2605.27970","title":"Geometry of Human Perceptual Domains Emerges Transiently in LLM Representations","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2607.08946","title":"Training, Reading, and Editing Legible Transformers","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2608.05162","title":"PoolBench: A Benchmark for Pooling Strategies in Concept Representation Evaluation for Decoder-Only LLMs","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2609.19150","title":"Sampling Reveals Style: Unsupervised, Training-Free Discovery of Prompt-Conditional Stylistic Axes in LLM Activations","created":"2026-07-20","cited_by_count":1,"area":null},{"id":"2406.07990","title":"Topological quantification of ambiguity in semantic search","created":"2024-06-12","cited_by_count":0,"area":null},{"id":"2503.20278","title":"The cell as a token: high-dimensional geometry in language models and cell embeddings","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2511.04312","title":"Probing the Probes: Methods and Metrics for Concept Alignment","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2512.12469","title":"Sparse Concept Anchoring for Interpretable and Controllable Neural Representations","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2601.06575","title":"Are Emotions Arranged in a Circle? Geometric Analysis of Emotion Representations via Hyperspherical Contrastive Learning","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2602.01687","title":"Functional Subspace, where language models can use vector algebra to solve problems","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.04931","title":"Emergent Causal-Geometric Dynamics Across Depth in Large Language Models","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2604.07095","title":"Multilingual Embedding Probes Fail to Generalize Across Learner Corpora","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2605.00847","title":"H-Probes: Extracting Hierarchical Structures From Latent Representations of Language Models","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2605.03052","title":"How Language Models Process Negation","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.06196","title":"The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.01302","title":"Structure and Scale in Simplicial Sequence Modelling","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.03645","title":"The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.05079","title":"Fast & Faithful Function Vectors","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.14347","title":"When Language Representations Interact: Separability and Cross-Lingual Effects in LLMs","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.04167","title":"Geometry of Ordinal Representations in Language Models","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2607.10578","title":"Laguerre Geometry for Interpreting Large Language Models","created":"2026-07-12","cited_by_count":0,"area":null},{"id":"2607.12279","title":"A Shared Subcircuit Lets LLMs Count Down Across Tasks","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2608.16650","title":"PCA-guided Activation Scaling for Monotonic Bidirectional Control over LLM Sycophancy","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.26887","title":"Planting a Latent Variable in Natural-Looking Text: a More Realistic Test of Belief States in LLMs and Their Link to Concept Geometry","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.01551","title":"What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.04721","title":"Locating and Steering Refusal Beyond Attention","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.05721","title":"Recovering Temporal and Geographic Signals from Language Model Embeddings","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.05743","title":"Some Tokens Behave like Magnets: Revealing Linguistic Organization in the Layers of Language Models","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.13072","title":"MAxBench: A Multinomial Concept Recovery Benchmark","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.22224","title":"From Trait Vectors to Circuits: Tracing Refusal and Sycophancy Through Language Models","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.22522","title":"When Cosine Similarity Fails to Reflect Linearly Accessible Structure in Dialogue Models","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.22695","title":"A Survey on the Linear Representation Hypothesis","created":"2026-09-19","cited_by_count":0,"area":null},{"id":"2609.24352","title":"Few-Shot Demonstrations Elicit the Use of In-Context World Representations in LLMs","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.27158","title":"The Linear Representation Hypothesis Needs a Group Action","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.32619","title":"Intuition vectors","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.35351","title":"Interference Beyond Geometry in Concept Extraction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35970","title":"Causal and Interpretable Structures in LLM Compositional Tasks","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37659","title":"Are In-Context Images Worth 10 Dimensions?","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38181","title":"Large Language Models are Approximate Survival Estimators","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2609.38718","title":"MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection Adaptation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.00647","title":"Group-Invariant Statistics Determine Embedding Geometry: Harmonic Analysis of Representations from Bach to the Night Sky","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":"100"}