{"total":92,"rows":[{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334,"area":null},{"id":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159,"area":null},{"id":"2203.12221","title":"Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)","created":"2022-03-23","cited_by_count":122,"area":null},{"id":"2105.15134","title":"Toward Understanding the Feature Learning Process of Self-supervised Contrastive Learning","created":"2021-05-31","cited_by_count":119,"area":null},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119,"area":null},{"id":"2103.15949","title":"Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors","created":"2021-03-29","cited_by_count":108,"area":null},{"id":"2504.02234","title":"LLM Social Simulations Are a Promising Research Method","created":"2025-04-03","cited_by_count":99,"area":null},{"id":"2506.19823","title":"Persona Features Control Emergent Misalignment","created":"2025-06-24","cited_by_count":86,"area":null},{"id":"2403.03867","title":"On the Origins of Linear Representations in Large Language Models","created":"2024-03-06","cited_by_count":79,"area":null},{"id":"2310.00492","title":"From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning","created":"2023-09-30","cited_by_count":56,"area":null},{"id":"2310.17230","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2403.08946","title":"Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era","created":"2024-03-13","cited_by_count":46,"area":null},{"id":"2310.06714","title":"Exploring Memorization in Fine-tuned Language Models","created":"2023-10-10","cited_by_count":45,"area":null},{"id":"2406.12907","title":"Reconciling Kaplan and Chinchilla Scaling Laws","created":"2024-06-12","cited_by_count":39,"area":null},{"id":"2305.15614","title":"Reverse Engineering Self-Supervised Learning","created":"2023-05-24","cited_by_count":33,"area":null},{"id":"2305.16536","title":"Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression","created":"2023-05-25","cited_by_count":30,"area":null},{"id":"2503.10996","title":"Taming Knowledge Conflicts in Language Models","created":"2025-03-14","cited_by_count":30,"area":null},{"id":"2408.09503","title":"Out-of-distribution generalization via composition: a lens through induction heads in Transformers","created":"2024-08-18","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":"2305.13175","title":"Discovering Universal Geometry in Embeddings with ICA","created":"2023-05-22","cited_by_count":19,"area":null},{"id":"2406.04331","title":"PaCE: Parsimonious Concept Engineering for Large Language Models","created":"2024-06-06","cited_by_count":19,"area":null},{"id":"2502.08009","title":"The Geometry of Prompting: Unveiling Distinct Mechanisms of Task Adaptation in Language Models","created":"2025-02-11","cited_by_count":18,"area":null},{"id":"2503.01824","title":"From superposition to sparse codes: interpretable representations in neural networks","created":"2025-03-03","cited_by_count":16,"area":null},{"id":"2301.00709","title":"Tsetlin Machine Embedding: Representing Words Using Logical Expressions","created":"2023-01-02","cited_by_count":15,"area":null},{"id":"2407.06076","title":"Understanding Visual Feature Reliance through the Lens of Complexity","created":"2024-07-08","cited_by_count":15,"area":null},{"id":"2104.08809","title":"SciCo: Hierarchical Cross-Document Coreference for Scientific Concepts","created":"2021-04-18","cited_by_count":14,"area":null},{"id":"2410.21331","title":"Beyond Interpretability: The Gains of Feature Monosemanticity on Model Robustness","created":"2024-10-27","cited_by_count":13,"area":null},{"id":"2501.08145","title":"Refusal Behavior in Large Language Models: A Nonlinear Perspective","created":"2025-01-14","cited_by_count":13,"area":null},{"id":"2503.08980","title":"I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?","created":"2025-03-12","cited_by_count":13,"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":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11,"area":null},{"id":"2105.10360","title":"Multi-source Learning via Completion of Block-wise Overlapping Noisy Matrices","created":"2021-05-21","cited_by_count":10,"area":null},{"id":"2502.00620","title":"Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions","created":"2025-02-02","cited_by_count":10,"area":null},{"id":"2406.11624","title":"Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers","created":"2024-06-17","cited_by_count":9,"area":null},{"id":"2106.08495","title":"Improving Entity Linking through Semantic Reinforced Entity Embeddings","created":"2021-06-16","cited_by_count":8,"area":null},{"id":"2106.14365","title":"Integrating topic modeling and word embedding to characterize violent deaths","created":"2021-06-28","cited_by_count":8,"area":null},{"id":"2104.07198","title":"Ultra-High Dimensional Sparse Representations with Binarization for Efficient Text Retrieval","created":"2021-04-15","cited_by_count":7,"area":null},{"id":"2209.00445","title":"Interpreting Embedding Spaces by Conceptualization","created":"2022-08-22","cited_by_count":6,"area":null},{"id":"2406.17837","title":"Transformer Normalisation Layers and the Independence of Semantic Subspaces","created":"2024-06-25","cited_by_count":6,"area":null},{"id":"2101.10448","title":"PolyLM: Learning about Polysemy through Language Modeling","created":"2021-01-25","cited_by_count":5,"area":null},{"id":"2107.10413","title":"Theoretical foundations and limits of word embeddings: what types of meaning can they capture?","created":"2021-07-22","cited_by_count":5,"area":null},{"id":"2112.08491","title":"Human Languages with Greater Information Density Increase Communication Speed, but Decrease Conversation Breadth","created":"2021-12-15","cited_by_count":5,"area":null},{"id":"2312.15611","title":"Inference of Dependency Knowledge Graph for Electronic Health Records","created":"2023-12-25","cited_by_count":5,"area":null},{"id":"2505.21364","title":"Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2506.03790","title":"Attention-Only Transformers via Unrolled Subspace Denoising","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2606.25008","title":"Neural Scaling Universality: If Exponents Are Fixed, Time to Understand Coefficients","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2105.08585","title":"Revisiting Additive Compositionality: AND, OR and NOT Operations with Word Embeddings","created":"2021-05-18","cited_by_count":4,"area":null},{"id":"2505.15811","title":"On the creation of narrow AI: hierarchy and nonlocality of neural network skills","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2103.15330","title":"Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2310.07837","title":"Measuring Feature Sparsity in Language Models","created":"2023-10-11","cited_by_count":3,"area":null},{"id":"2403.14926","title":"Contrastive Learning on Multimodal Analysis of Electronic Health Records","created":"2024-03-22","cited_by_count":3,"area":null},{"id":"2505.24539","title":"Localizing Persona Representations in LLMs","created":"2025-05-30","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":"2606.03043","title":"The Geometry of LLM-as-Judge: Why Inter-LLM Consensus Is Not Human Alignment","created":"2026-06-02","cited_by_count":3,"area":null},{"id":"2101.00480","title":"A multi-modal approach towards mining social media data during natural disasters -- a case study of Hurricane Irma","created":"2021-01-02","cited_by_count":2,"area":null},{"id":"2111.01023","title":"Interpretable contrastive word mover's embedding","created":"2021-11-01","cited_by_count":2,"area":null},{"id":"2304.13597","title":"Shades of meaning: Uncovering the geometry of ambiguous word representations through contextualised language models","created":"2023-04-26","cited_by_count":2,"area":null},{"id":"2410.10153","title":"Diagnosing Hate Speech Classification: Where Do Humans and Machines Disagree, and Why?","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2501.16374","title":"SAFR: Neuron Redistribution for Interpretability","created":"2025-01-23","cited_by_count":2,"area":null},{"id":"2503.10664","title":"Semantic Wave Functions: Exploring Meaning in Large Language Models Through Quantum Formalism","created":"2025-03-09","cited_by_count":2,"area":null},{"id":"2505.08348","title":"Geometry of Semantics in Next-Token Prediction: How Optimization Implicitly Organizes Linguistic Representations","created":"2025-05-13","cited_by_count":2,"area":null},{"id":"2505.23117","title":"Decom-Renorm-Merge: Model Merging on the Right Space Improves Multitasking","created":"2025-05-29","cited_by_count":2,"area":null},{"id":"2509.24198","title":"Negative Pre-activations Differentiate Syntax","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2601.03657","title":"In Search of Grandmother Cells: Tracing Interpretable Neurons in Tabular Representations","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2601.04855","title":"Rethinking GNNs and Missing Features: Challenges, Evaluation and a Robust Solution","created":"2026-01-08","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":"2507.06427","title":"Exploring Task Performance with Interpretable Models via Sparse Auto-Encoders","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2507.19680","title":"Feature learning is decoupled from generalization in high capacity neural networks","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2510.17924","title":"Efficient Toxicity Detection in Gaming Chats: A Comparative Study of Embeddings, Fine-Tuned Transformers and LLMs","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2606.03990","title":"Neuron Populations Exhibit Divergent Selectivity with Scale","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2101.11505","title":"Low-skilled Occupations Face the Highest Upskilling Pressure","created":"2021-01-27","cited_by_count":0,"area":null},{"id":"2108.12459","title":"From Pivots to Graphs: Augmented CycleDensity as a Generalization to One Time InverseConsultation","created":"2021-08-27","cited_by_count":0,"area":null},{"id":"2111.10750","title":"More Romanian word embeddings from the RETEROM project","created":"2021-11-21","cited_by_count":0,"area":null},{"id":"2205.00148","title":"To Know by the Company Words Keep and What Else Lies in the Vicinity","created":"2022-04-30","cited_by_count":0,"area":null},{"id":"2208.05462","title":"The Analysis about Building Cross-lingual Sememe Knowledge Base Based on Deep Clustering Network","created":"2022-08-10","cited_by_count":0,"area":null},{"id":"2210.14815","title":"On the Curious Case of $\\ell_2$ norm of Sense Embeddings","created":"2022-10-26","cited_by_count":0,"area":null},{"id":"2302.05657","title":"Dialectograms: Machine Learning Differences between Discursive Communities","created":"2023-02-11","cited_by_count":0,"area":null},{"id":"2306.04133","title":"Answering Compositional Queries with Set-Theoretic Embeddings","created":"2023-06-07","cited_by_count":0,"area":null},{"id":"2306.14135","title":"Interpretable Neural Embeddings with Sparse Self-Representation","created":"2023-06-25","cited_by_count":0,"area":null},{"id":"2310.20144","title":"EELBERT: Tiny Models through Dynamic Embeddings","created":"2023-10-31","cited_by_count":0,"area":null},{"id":"2502.05407","title":"Dictionary Learning: The Complexity of Learning Sparse Superposed Features with Feedback","created":"2025-02-08","cited_by_count":0,"area":null},{"id":"2502.10875","title":"A Geometric Approach to Personalized Recommendation with Set-Theoretic Constraints Using Box Embeddings","created":"2025-02-15","cited_by_count":0,"area":null},{"id":"2505.13742","title":"Understanding Task Representations in Neural Networks via Bayesian Ablation","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2510.01288","title":"Microsaccade-Inspired Probing: Positional Encoding Perturbations Reveal LLM Misbehaviours","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2601.11572","title":"Discrete Semantic States and Hamiltonian Dynamics in LLM Embedding Spaces","created":"2025-12-29","cited_by_count":0,"area":null},{"id":"2604.16487","title":"Geometry-Aware CLIP Retrieval via Local Cross-Modal Alignment and Steering","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2606.13934","title":"Adversarial Concept Search: Predicting Compositional Errors From Feature Geometry","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2608.00410","title":"Where did the ambiguity go? Examining how multimodal models interpret polysemous words","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.24748","title":"Method, Mind, and Morality: How People Make Sense of Artificial Intelligence","created":"2026-08-25","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":"2609.36455","title":"Emergent phases of superposition: from partial to full representation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00910","title":"The Geometry of Contextual Relations: Language Models Address Facts by Order of Mention","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}