{"total":89,"rows":[{"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":"2409.03752","title":"Attention Heads of Large Language Models: A Survey","created":"2024-09-05","cited_by_count":67,"area":null},{"id":"2407.10827","title":"LLM Circuit Analyses Are Consistent Across Training and Scale","created":"2024-07-15","cited_by_count":63,"area":null},{"id":"2501.16265","title":"Training Dynamics of In-Context Learning in Linear Attention","created":"2025-01-27","cited_by_count":46,"area":null},{"id":"2406.09519","title":"Talking Heads: Understanding Inter-layer Communication in Transformer Language Models","created":"2024-06-13","cited_by_count":41,"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":"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":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2409.09951","title":"Optimal ablation for interpretability","created":"2024-09-16","cited_by_count":25,"area":null},{"id":"2505.17863","title":"The emergence of sparse attention: impact of data distribution and benefits of repetition","created":"2025-05-23","cited_by_count":25,"area":null},{"id":"2410.09695","title":"Can In-context Learning Really Generalize to Out-of-distribution Tasks?","created":"2024-10-13","cited_by_count":23,"area":null},{"id":"2410.23042","title":"Toward Understanding In-context vs. In-weight Learning","created":"2024-10-30","cited_by_count":19,"area":null},{"id":"2505.17097","title":"Make LVLMs Focus: Context-Aware Attention Modulation for Better Multimodal In-Context Learning","created":"2025-05-21","cited_by_count":19,"area":"mllm"},{"id":"2410.04468","title":"Revisiting In-context Learning Inference Circuit in Large Language Models","created":"2024-10-06","cited_by_count":17,"area":"mechinterp"},{"id":"2410.10626","title":"Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family Experts","created":"2024-10-14","cited_by_count":17,"area":"moe"},{"id":"2503.05631","title":"Strategy Coopetition Explains the Emergence and Transience of In-Context Learning","created":"2025-03-07","cited_by_count":17,"area":null},{"id":"2405.14992","title":"Linking In-context Learning in Transformers to Human Episodic Memory","created":"2024-05-23","cited_by_count":15,"area":null},{"id":"2405.19162","title":"Does learning the right latent variables necessarily improve in-context learning?","created":"2024-05-29","cited_by_count":13,"area":null},{"id":"2502.12131","title":"Transformer Dynamics: A neuroscientific approach to interpretability of large language models","created":"2025-02-17","cited_by_count":11,"area":"mechinterp"},{"id":"2505.16694","title":"Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence","created":"2025-05-22","cited_by_count":10,"area":null},{"id":"2505.18752","title":"Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning","created":"2025-05-24","cited_by_count":10,"area":null},{"id":"2512.08417","title":"Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs","created":"2025-12-09","cited_by_count":10,"area":"agents"},{"id":"2601.21996","title":"Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units","created":"2026-01-29","cited_by_count":10,"area":"mechinterp"},{"id":"2605.29548","title":"Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention","created":"2026-05-28","cited_by_count":10,"area":null},{"id":"2505.15105","title":"Mechanistic evaluation of Transformers and state space models","created":"2025-05-21","cited_by_count":9,"area":"ssm"},{"id":"2509.17588","title":"Interpreting Attention Heads for Image-to-Text Information Flow in Large Vision-Language Models","created":"2025-09-22","cited_by_count":9,"area":"mllm"},{"id":"2505.05145","title":"Understanding In-context Learning of Addition via Activation Subspaces","created":"2025-05-08","cited_by_count":8,"area":null},{"id":"2601.22364","title":"Context Structure Reshapes the Representational Geometry of Language Models","created":"2026-01-29","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":"2410.09343","title":"ELICIT: LLM Augmentation via External In-Context Capability","created":"2024-10-12","cited_by_count":7,"area":null},{"id":"2506.13688","title":"What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers","created":"2025-06-16","cited_by_count":7,"area":null},{"id":"2511.16893","title":"Predicting the Emergence of Induction Heads in Language Model Pretraining","created":"2025-11-21","cited_by_count":7,"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":"2505.21785","title":"Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2410.05448","title":"Task Diversity Shortens the ICL Plateau","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2505.09027","title":"Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation","created":"2025-05-13","cited_by_count":5,"area":null},{"id":"2506.13253","title":"Distinct Computations Emerge From Compositional Curricula in In-Context Learning","created":"2025-06-16","cited_by_count":5,"area":null},{"id":"2509.22831","title":"Toward a Theory of Generalizability in LLM Mechanistic Interpretability Research","created":"2025-09-26","cited_by_count":5,"area":"mechinterp"},{"id":"2512.16902","title":"In-Context Algebra","created":"2025-12-18","cited_by_count":5,"area":null},{"id":"2601.10266","title":"Measuring Affinity between Attention-Head Weight Subspaces via the Projection Kernel","created":"2026-01-15","cited_by_count":5,"area":null},{"id":"2601.20796","title":"Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern Transformers","created":"2026-01-28","cited_by_count":5,"area":"mllm"},{"id":"2501.06256","title":"Unlocking In-Context Learning for Natural Datasets Beyond Language Modelling","created":"2025-01-09","cited_by_count":4,"area":null},{"id":"2502.06902","title":"Emergence of Episodic Memory in Transformers: Characterizing Changes in Temporal Structure of Attention Scores During Training","created":"2025-02-09","cited_by_count":4,"area":null},{"id":"2510.10425","title":"Softmax $\\geq$ Linear: Transformers may learn to classify in-context by kernel gradient descent","created":"2025-10-12","cited_by_count":4,"area":null},{"id":"2603.29805","title":"From Density Matrices to Phase Transitions in Deep Learning: Spectral Early Warnings and Interpretability","created":"2026-03-31","cited_by_count":4,"area":null},{"id":"2604.12151","title":"Distinct mechanisms underlying in-context learning in transformers","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2603.20969","title":"Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge","created":"2026-03-21","cited_by_count":3,"area":"lr"},{"id":"2604.08764","title":"Revisiting Anisotropy in Language Transformers: The Geometry of Learning Dynamics","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2509.23204","title":"Steering Prepositional Phrases in Language Models: A Case of with-headed Adjectival and Adverbial Complements in Gemma-2","created":"2025-09-27","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":"2510.17256","title":"Explainability of Large Language Models: Opportunities and Challenges toward Generating Trustworthy Explanations","created":"2025-10-20","cited_by_count":2,"area":"mechinterp"},{"id":"2602.00533","title":"Convergent World Representations and Divergent Tasks","created":"2026-01-31","cited_by_count":2,"area":null},{"id":"2603.06248","title":"Gradient Flow Polarizes Softmax Outputs towards Low-Entropy Solutions","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2603.06592","title":"Hierarchical Latent Structures in Data Generation Process Unify Mechanistic Phenomena across Scale","created":"2026-02-04","cited_by_count":2,"area":"mechinterp"},{"id":"2604.13403","title":"Why Multimodal In-Context Learning Lags Behind? Unveiling the Inner Mechanisms and Bottlenecks","created":"2026-04-15","cited_by_count":2,"area":null},{"id":"2605.28854","title":"Large language models reorganize representational geometry during in-context learning","created":"2026-05-16","cited_by_count":2,"area":null},{"id":"2407.10949","title":"Representing Rule-based Chatbots with Transformers","created":"2024-07-15","cited_by_count":1,"area":null},{"id":"2411.07071","title":"Universal Response and Emergence of Induction in LLMs","created":"2024-11-11","cited_by_count":1,"area":null},{"id":"2505.09855","title":"An evolutionary perspective on modes of learning in Transformers","created":"2025-05-14","cited_by_count":1,"area":null},{"id":"2506.04289","title":"Relational reasoning and inductive bias in transformers and large language models","created":"2025-06-04","cited_by_count":1,"area":"lr"},{"id":"2511.19328","title":"Understanding the Staged Dynamics of Transformers in Learning Latent Structure","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2603.18446","title":"UT-ACA: Uncertainty-Triggered Adaptive Context Allocation for Long-Context Inference","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2604.10848","title":"Transformers Learn Latent Mixture Models In-Context via Mirror Descent","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2607.02800","title":"Induction Heads Interpolate N-Grams","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.07316","title":"Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning","created":"2026-07-08","cited_by_count":1,"area":"lr"},{"id":"2504.09393","title":"Vision Transformers Exhibit Human-Like Biases: Evidence of Orientation and Color Selectivity, Categorical Perception, and Phase Transitions","created":"2025-04-13","cited_by_count":0,"area":null},{"id":"2505.14233","title":"Mechanistic Fine-tuning for In-context Learning","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2505.17073","title":"Mechanistic Interpretability of GPT-like Models on Summarization Tasks","created":"2025-05-20","cited_by_count":0,"area":"mechinterp"},{"id":"2506.03434","title":"Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Models","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2507.01414","title":"Decomposing Prediction Mechanisms for In-Context Recall","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2510.11390","title":"Medical Interpretability and Knowledge Maps of Large Language Models","created":"2025-10-13","cited_by_count":0,"area":"mechinterp"},{"id":"2511.05743","title":"In-Context Learning Without Copying","created":"2025-11-07","cited_by_count":0,"area":null},{"id":"2602.07562","title":"Gaussian Match-and-Copy: A Minimalist Benchmark for Studying Transformer Induction","created":"2026-02-07","cited_by_count":0,"area":null},{"id":"2604.01094","title":"Temporal Dependencies in In-Context Learning: The Role of Induction Heads","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2604.01601","title":"Contrast Matters: Understanding Robustness of In-Context Fine-Tuning to Target-Context Relatedness","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.08405","title":"Belief or Circuitry? Causal Evidence for In-Context Graph Learning","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2607.04846","title":"Pretraining Curricula Enable Selective Fine-tuning","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.06621","title":"Fingerprint, Not Blueprint: How Positional Schemes Set the Default Spectral Algebra of Attention","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.24471","title":"Grounding latent algorithm routing in transformer reasoning","created":"2026-07-27","cited_by_count":0,"area":"lr"},{"id":"2607.27281","title":"The Kinetics of Training: A Driven-Nucleation Rate Law for Emergence, Plasticity Loss, and Circuit Control in Language Models","created":"2026-07-29","cited_by_count":0,"area":"mechinterp"},{"id":"2608.13385","title":"When Is a Task Vector Enough? An Empirical Theory of Implicit Multimodal ICL","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.24460","title":"Shortcut Before Circuit: Document Statistics Time In-Context Conflict Resolution","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.29034","title":"A Unifying Perspective on Language Model Representations: From Filler-Role Structure to Mechanistic Interpretability","created":"2026-08-29","cited_by_count":0,"area":"mechinterp"},{"id":"2609.15545","title":"The Token Before the Value Is the Key: How Hybrid Architectures Organize Induction Circuits","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.32991","title":"What Should Data Teach? Moving Bottlenecks Across Circuit, Store, and Use","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33093","title":"How Linear Attention Remembers","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.39604","title":"Why Do Conventional World Models Fail to Learn Cellular Automata?","created":"2026-09-30","cited_by_count":0,"area":"wm"},{"id":"2610.18725","title":"Learning Source Structure: Bayesian Prediction with Transformers","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.20337","title":"Training Dynamics of Transformers on Unbounded Inputs: Attention Learning Can Lag Output Layer Learning","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}