{"total":98,"rows":[{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716,"area":null},{"id":"2309.16042","title":"Towards Best Practices of Activation Patching in Language Models: Metrics and Methods","created":"2023-09-27","cited_by_count":359,"area":"mechinterp"},{"id":"2310.15916","title":"In-Context Learning Creates Task Vectors","created":"2023-10-24","cited_by_count":312,"area":null},{"id":"2310.15213","title":"Function Vectors in Large Language Models","created":"2023-10-23","cited_by_count":308,"area":null},{"id":"2308.09124","title":"Linearity of Relation Decoding in Transformer Language Models","created":"2023-08-17","cited_by_count":200,"area":null},{"id":"2310.08744","title":"Circuit Component Reuse Across Tasks in Transformer Language Models","created":"2023-10-12","cited_by_count":108,"area":"mechinterp"},{"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":"2406.12775","title":"Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries","created":"2024-06-18","cited_by_count":78,"area":null},{"id":"2312.09230","title":"Successor Heads: Recurring, Interpretable Attention Heads In The Wild","created":"2023-12-14","cited_by_count":77,"area":null},{"id":"2607.15495","title":"Verbalizable Representations Form a Global Workspace in Language Models","created":"2026-07-16","cited_by_count":75,"area":null},{"id":"2411.04986","title":"The Semantic Hub Hypothesis: Language Models Share Semantic Representations Across Languages and Modalities","created":"2024-11-07","cited_by_count":69,"area":null},{"id":"2405.17969","title":"Knowledge Circuits in Pretrained Transformers","created":"2024-05-28","cited_by_count":60,"area":"mechinterp"},{"id":"2310.14491","title":"Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models","created":"2023-10-23","cited_by_count":50,"area":"lr"},{"id":"2506.03093","title":"From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit","created":"2025-06-03","cited_by_count":49,"area":"mechinterp"},{"id":"2310.17230","title":"Codebook Features: Sparse and Discrete Interpretability for Neural Networks","created":"2023-10-26","cited_by_count":48,"area":null},{"id":"2410.05864","title":"From Tokens to Words: On the Inner Lexicon of LLMs","created":"2024-10-08","cited_by_count":48,"area":null},{"id":"2309.10312","title":"Rigorously Assessing Natural Language Explanations of Neurons","created":"2023-09-19","cited_by_count":45,"area":null},{"id":"2406.03445","title":"Pre-trained Large Language Models Use Fourier Features to Compute Addition","created":"2024-06-05","cited_by_count":39,"area":"lr"},{"id":"2410.06331","title":"Locate-then-edit for Multi-hop Factual Recall under Knowledge Editing","created":"2024-10-08","cited_by_count":37,"area":null},{"id":"2311.07470","title":"Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers","created":"2023-11-13","cited_by_count":36,"area":"mllm"},{"id":"2407.15018","title":"Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions","created":"2024-07-21","cited_by_count":35,"area":null},{"id":"2504.04633","title":"M$^2$IV: Towards Efficient and Fine-grained Multimodal In-Context Learning via Representation Engineering","created":"2025-04-06","cited_by_count":35,"area":"mllm"},{"id":"2410.09223","title":"The Same But Different: Structural Similarities and Differences in Multilingual Language Modeling","created":"2024-10-11","cited_by_count":28,"area":"mechinterp"},{"id":"2310.11409","title":"LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks","created":"2023-10-17","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":"2504.12459","title":"On Linear Representations and Pretraining Data Frequency in Language Models","created":"2025-04-16","cited_by_count":23,"area":null},{"id":"2310.03686","title":"DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers","created":"2023-10-05","cited_by_count":22,"area":null},{"id":"2405.01964","title":"Position: Understanding LLMs Requires More Than Statistical Generalization","created":"2024-05-03","cited_by_count":21,"area":null},{"id":"2505.20546","title":"Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipeline","created":"2025-05-26","cited_by_count":21,"area":null},{"id":"2503.08588","title":"BiasEdit: Debiasing Stereotyped Language Models via Model Editing","created":"2025-03-11","cited_by_count":18,"area":null},{"id":"2506.05140","title":"AudioLens: A Closer Look at Auditory Attribute Perception of Large Audio-Language Models","created":"2025-06-05","cited_by_count":18,"area":null},{"id":"2510.18871","title":"How Do LLMs Use Their Depth?","created":"2025-10-21","cited_by_count":16,"area":null},{"id":"2310.17611","title":"Uncovering Meanings of Embeddings via Partial Orthogonality","created":"2023-10-26","cited_by_count":15,"area":null},{"id":"2404.11225","title":"In-Context Learning State Vector with Inner and Momentum Optimization","created":"2024-04-17","cited_by_count":15,"area":null},{"id":"2410.23501","title":"All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling","created":"2024-10-30","cited_by_count":14,"area":null},{"id":"2505.18651","title":"On the Emergence of Linear Analogies in Word Embeddings","created":"2025-05-24","cited_by_count":13,"area":null},{"id":"2311.04354","title":"Uncovering Intermediate Variables in Transformers using Circuit Probing","created":"2023-11-07","cited_by_count":12,"area":null},{"id":"2506.01115","title":"Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer","created":"2025-06-01","cited_by_count":12,"area":"lr"},{"id":"2406.01352","title":"Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience","created":"2024-06-03","cited_by_count":11,"area":null},{"id":"2502.05390","title":"Learning Task Representations from In-Context Learning","created":"2025-02-08","cited_by_count":11,"area":null},{"id":"2506.04179","title":"SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2309.00244","title":"NeuroSurgeon: A Toolkit for Subnetwork Analysis","created":"2023-09-01","cited_by_count":9,"area":null},{"id":"2412.12276","title":"Emergence and Effectiveness of Task Vectors in In-Context Learning: An Encoder Decoder Perspective","created":"2024-12-16","cited_by_count":9,"area":null},{"id":"2503.16356","title":"CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners","created":"2025-03-20","cited_by_count":9,"area":null},{"id":"2505.23701","title":"Can LLMs Reason Abstractly Over Math Word Problems Without CoT? Disentangling Abstract Formulation From Arithmetic Computation","created":"2025-05-29","cited_by_count":8,"area":"lr"},{"id":"2509.22854","title":"Train Once, Reuse Everywhere: Generalizable Implicit In-Context Learning by Routing Attention","created":"2025-09-26","cited_by_count":8,"area":null},{"id":"2510.01685","title":"How Do Language Models Compose Functions?","created":"2025-10-02","cited_by_count":8,"area":null},{"id":"2410.09343","title":"ELICIT: LLM Augmentation via External In-Context Capability","created":"2024-10-12","cited_by_count":7,"area":null},{"id":"2508.05776","title":"Whither symbols in the era of advanced neural networks?","created":"2025-08-07","cited_by_count":7,"area":null},{"id":"2310.10899","title":"Instilling Inductive Biases with Subnetworks","created":"2023-10-17","cited_by_count":6,"area":null},{"id":"2406.13131","title":"When Parts Are Greater Than Sums: Individual LLM Components Can Outperform Full Models","created":"2024-06-19","cited_by_count":6,"area":null},{"id":"2505.22630","title":"Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMs","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2506.18141","title":"Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models","created":"2025-06-22","cited_by_count":6,"area":"mechinterp"},{"id":"2511.19265","title":"Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks","created":"2025-11-24","cited_by_count":6,"area":"mechinterp"},{"id":"2310.15477","title":"CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model","created":"2023-10-24","cited_by_count":5,"area":"alignment"},{"id":"2506.04461","title":"Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey","created":"2025-06-04","cited_by_count":5,"area":null},{"id":"2507.07544","title":"Position: We Need An Algorithmic Understanding of Generative AI","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2602.01605","title":"Universal Redundancies in Time Series Foundation Models","created":"2026-02-02","cited_by_count":5,"area":null},{"id":"2410.06024","title":"Jet Expansions of Residual Computation","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2502.17355","title":"On Relation-Specific Neurons in Large Language Models","created":"2025-02-24","cited_by_count":4,"area":null},{"id":"2506.10641","title":"Spelling-out is not Straightforward: LLMs' Capability of Tokenization from Token to Characters","created":"2025-06-12","cited_by_count":4,"area":null},{"id":"2604.07886","title":"Linear Representations of Hierarchical Concepts in Language Models","created":"2026-04-09","cited_by_count":4,"area":"mechinterp"},{"id":"2310.03149","title":"Attributing Learned Concepts in Neural Networks to Training Data","created":"2023-10-04","cited_by_count":3,"area":null},{"id":"2504.14107","title":"Signatures of human-like processing in Transformer forward passes","created":"2025-04-18","cited_by_count":3,"area":null},{"id":"2506.16370","title":"Can structural correspondences ground real world representational content in Large Language Models?","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2506.16975","title":"Latent Concept Disentanglement in Transformer-based Language Models","created":"2025-06-20","cited_by_count":3,"area":null},{"id":"2506.20746","title":"Dynamic Weight Grafting: Localizing Finetuned Factual Knowledge in Transformers","created":"2025-06-25","cited_by_count":3,"area":null},{"id":"2509.24169","title":"Task Vectors, Learned Not Extracted: Performance Gains and Mechanistic Insight","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2605.18830","title":"In-Context Learning Operates as Concept Subspace Learning","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2509.12065","title":"Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspect","created":"2025-09-15","cited_by_count":2,"area":null},{"id":"2509.24164","title":"Localizing Task Recognition and Task Learning in In-Context Learning via Attention Head Analysis","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2510.24256","title":"From Memorization to Reasoning in the Spectrum of Loss Curvature","created":"2025-10-28","cited_by_count":2,"area":"lr"},{"id":"2603.10771","title":"Word Recovery in Large Language Models Enables Character-Level Tokenization Robustness","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2502.20475","title":"Promote, Suppress, Iterate: How Language Models Answer One-to-Many Factual Queries","created":"2025-02-27","cited_by_count":1,"area":null},{"id":"2507.14640","title":"Linear Relational Decoding of Morphology in Language Models","created":"2025-07-19","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":"2510.09790","title":"Mapping Semantic & Syntactic Relationships with Geometric Rotation","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2510.11268","title":"Exploring and Leveraging Class Vectors for Classifier Editing","created":"2025-10-13","cited_by_count":1,"area":null},{"id":"2510.17001","title":"Vocab Diet: Reshaping the Vocabulary of LLMs via Vector Arithmetic","created":"2025-10-19","cited_by_count":1,"area":null},{"id":"2605.12908","title":"The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.16023","title":"Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.16600","title":"Where Pretraining writes and Alignment reads: the asymmetry of Transformer weight space","created":"2026-05-15","cited_by_count":1,"area":"alignment"},{"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":"2608.15507","title":"Do Language Models Consistently Encode the Current Year?","created":"2026-08-16","cited_by_count":1,"area":"lr"},{"id":"2505.08389","title":"Towards Contamination Resistant Benchmarks","created":"2025-05-13","cited_by_count":0,"area":null},{"id":"2506.20083","title":"Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder","created":"2025-06-25","cited_by_count":0,"area":"mechinterp"},{"id":"2603.13459","title":"Reconciling In-Context and In-Weight Learning via Dual Representation Space Encoding","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.16196","title":"PanguMotion: Continuous Driving Motion Forecasting with Pangu Transformers","created":"2026-03-17","cited_by_count":0,"area":"driving"},{"id":"2604.06501","title":"Transformer See, Transformer Do: Copying as an Intermediate Step in Learning Analogical Reasoning","created":"2026-04-07","cited_by_count":0,"area":"lr"},{"id":"2604.12426","title":"Do Transformers Use their Depth Adaptively? Evidence from a Relational Reasoning Task","created":"2026-04-14","cited_by_count":0,"area":"lr"},{"id":"2604.15842","title":"Disentangling Mathematical Reasoning in LLMs: A Methodological Investigation of Internal Mechanisms","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2605.22532","title":"Relational Linear Properties in Language Models: An Empirical Investigation","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.25384","title":"GeoMathCode: Understanding Interleaved Math-Code Reasoning for Geometry Problem Solving","created":"2026-05-25","cited_by_count":0,"area":"lr"},{"id":"2606.05079","title":"Fast & Faithful Function Vectors","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2607.00083","title":"Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust","created":"2026-06-30","cited_by_count":0,"area":"mechinterp"},{"id":"2607.26179","title":"Cognitive Convergence: Deep Similarities Between Large Language Models and Human Cognition","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.20139","title":"Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models","created":"2026-09-17","cited_by_count":0,"area":"mllm"},{"id":"2609.35970","title":"Causal and Interpretable Structures in LLM Compositional Tasks","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}