{"total":77,"rows":[{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623,"area":"mechinterp"},{"id":"2309.00941","title":"Emergent Linear Representations in World Models of Self-Supervised Sequence Models","created":"2023-09-02","cited_by_count":319,"area":"wm"},{"id":"2306.00297","title":"Transformers learn to implement preconditioned gradient descent for in-context learning","created":"2023-06-01","cited_by_count":279,"area":null},{"id":"2406.19384","title":"The Remarkable Robustness of LLMs: Stages of Inference?","created":"2024-06-27","cited_by_count":146,"area":null},{"id":"2407.02646","title":"A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models","created":"2024-07-02","cited_by_count":118,"area":"mechinterp"},{"id":"2401.12181","title":"Universal Neurons in GPT2 Language Models","created":"2024-01-22","cited_by_count":102,"area":"mechinterp"},{"id":"2305.16130","title":"Language Models Implement Simple Word2Vec-style Vector Arithmetic","created":"2023-05-25","cited_by_count":98,"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":"2410.08292","title":"Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?","created":"2024-10-10","cited_by_count":65,"area":null},{"id":"2405.15471","title":"Emergence of a High-Dimensional Abstraction Phase in Language Transformers","created":"2024-05-24","cited_by_count":56,"area":null},{"id":"2202.00275","title":"Architecture Matters in Continual Learning","created":"2022-02-01","cited_by_count":46,"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":"2402.15390","title":"Explorations of Self-Repair in Language Models","created":"2024-02-23","cited_by_count":39,"area":null},{"id":"2503.21073","title":"Shared Global and Local Geometry of Language Model Embeddings","created":"2025-03-27","cited_by_count":36,"area":null},{"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":"2405.18711","title":"Calibrating Reasoning in Language Models with Internal Consistency","created":"2024-05-29","cited_by_count":28,"area":"lr"},{"id":"2310.03686","title":"DecoderLens: Layerwise Interpretation of Encoder-Decoder Transformers","created":"2023-10-05","cited_by_count":22,"area":null},{"id":"2409.04185","title":"Residual Stream Analysis with Multi-Layer SAEs","created":"2024-09-06","cited_by_count":19,"area":"mechinterp"},{"id":"2501.10573","title":"The Intrinsic Dimension of Prompts in Internal Representations of Large Language Models","created":"2025-01-17","cited_by_count":17,"area":"mechinterp"},{"id":"2210.07998","title":"$\\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells","created":"2022-10-14","cited_by_count":15,"area":null},{"id":"2503.10679","title":"LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss","created":"2025-03-11","cited_by_count":14,"area":"mechinterp"},{"id":"2303.07677","title":"SR-init: An interpretable layer pruning method","created":"2023-03-14","cited_by_count":13,"area":null},{"id":"2407.07810","title":"Transformer Block Coupling and its Correlation with Generalization in LLMs","created":"2024-07-10","cited_by_count":10,"area":null},{"id":"2605.06510","title":"Is One Layer Enough? Understanding Inference Dynamics in Tabular Foundation Models","created":"2026-05-07","cited_by_count":10,"area":null},{"id":"2102.11011","title":"The Uncanny Similarity of Recurrence and Depth","created":"2021-02-22","cited_by_count":9,"area":null},{"id":"2210.06699","title":"Parameter-Efficient Masking Networks","created":"2022-10-13","cited_by_count":9,"area":null},{"id":"2404.05971","title":"Does Transformer Interpretability Transfer to RNNs?","created":"2024-04-09","cited_by_count":9,"area":"ssm"},{"id":"2410.23451","title":"Rethinking Deep Thinking: Stable Learning of Algorithms using Lipschitz Constraints","created":"2024-10-30","cited_by_count":9,"area":null},{"id":"2510.24907","title":"Understanding Multi-View Transformers","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2309.07315","title":"Traveling Words: A Geometric Interpretation of Transformers","created":"2023-09-13","cited_by_count":7,"area":null},{"id":"2202.02777","title":"Learning Features with Parameter-Free Layers","created":"2022-02-06","cited_by_count":5,"area":null},{"id":"2310.15690","title":"Power-Enhanced Residual Network for Function Approximation and Physics-Informed Inverse Problems","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2206.01261","title":"Entangled Residual Mappings","created":"2022-06-02","cited_by_count":4,"area":null},{"id":"2309.17357","title":"Module-wise Training of Neural Networks via the Minimizing Movement Scheme","created":"2023-09-29","cited_by_count":4,"area":null},{"id":"2407.07375","title":"Stable Weight Updating: A Key to Reliable PDE Solutions Using Deep Learning","created":"2024-07-10","cited_by_count":4,"area":null},{"id":"2410.06024","title":"Jet Expansions of Residual Computation","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2410.20035","title":"Training the Untrainable: Introducing Inductive Bias via Representational Alignment","created":"2024-10-26","cited_by_count":4,"area":null},{"id":"2508.10395","title":"XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization","created":"2025-08-14","cited_by_count":4,"area":"inference"},{"id":"2404.13855","title":"Understanding the role of FFNs in driving multilingual behaviour in LLMs","created":"2024-04-22","cited_by_count":3,"area":null},{"id":"2509.25045","title":"Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures","created":"2025-09-29","cited_by_count":3,"area":"mechinterp"},{"id":"2106.13919","title":"Pruning Edges and Gradients to Learn Hypergraphs from Larger Sets","created":"2021-06-26","cited_by_count":2,"area":null},{"id":"2111.07898","title":"Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorization","created":"2021-11-15","cited_by_count":2,"area":null},{"id":"2111.12330","title":"Hidden-Fold Networks: Random Recurrent Residuals Using Sparse Supermasks","created":"2021-11-24","cited_by_count":2,"area":null},{"id":"2312.09417","title":"DTP-Net: Learning to Reconstruct EEG signals in Time-Frequency Domain by Multi-scale Feature Reuse","created":"2023-11-27","cited_by_count":2,"area":null},{"id":"2504.13763","title":"Decoding Vision Transformers: the Diffusion Steering Lens","created":"2025-04-18","cited_by_count":2,"area":"mechinterp"},{"id":"2204.07412","title":"End-to-End Sensitivity-Based Filter Pruning","created":"2022-04-15","cited_by_count":1,"area":null},{"id":"2207.10237","title":"SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks","created":"2022-07-21","cited_by_count":1,"area":null},{"id":"2209.05253","title":"Transfer Learning and Vision Transformer based State-of-Health prediction of Lithium-Ion Batteries","created":"2022-09-07","cited_by_count":1,"area":null},{"id":"2210.00949","title":"Block-wise Training of Residual Networks via the Minimizing Movement Scheme","created":"2022-10-03","cited_by_count":1,"area":null},{"id":"2212.02687","title":"Vision Transformer Computation and Resilience for Dynamic Inference","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2312.16392","title":"Adaptive Depth Networks with Skippable Sub-Paths","created":"2023-12-27","cited_by_count":1,"area":null},{"id":"2410.19931","title":"Provable optimal transport with transformers: The essence of depth and prompt engineering","created":"2024-10-25","cited_by_count":1,"area":null},{"id":"2511.18105","title":"AdaPerceiver: Transformers with Adaptive Width, Depth, and Tokens","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2512.10547","title":"Unlocking the Address Book: Dissecting the Sparse Semantic Structure of LLM Key-Value Caches via Sparse Autoencoders","created":"2025-12-11","cited_by_count":1,"area":"inference"},{"id":"2607.08946","title":"Training, Reading, and Editing Legible Transformers","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2607.27656","title":"Looped Transformers with Source-Centered State Evolution","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.02064","title":"Geometry-Guided Layerwise FFN Width Allocation in Transformers","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.10251","title":"Off-Axis, On Purpose: Where a Transformer Computes Concepts and Why it Does So","created":"2026-08-10","cited_by_count":1,"area":null},{"id":"2609.29768","title":"Depth through recurrence: Looped transformers for flow-matching TTS","created":"2026-09-24","cited_by_count":1,"area":"diffusion"},{"id":"2210.11114","title":"Pruning by Active Attention Manipulation","created":"2022-10-20","cited_by_count":0,"area":null},{"id":"2211.05184","title":"Are All Edges Necessary? A Unified Framework for Graph Purification","created":"2022-11-09","cited_by_count":0,"area":null},{"id":"2407.08134","title":"Highway Networks for Improved Surface Reconstruction: The Role of Residuals and Weight Updates","created":"2024-07-11","cited_by_count":0,"area":null},{"id":"2408.00508","title":"Block-Operations: Using Modular Routing to Improve Compositional Generalization","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2412.07114","title":"TT-MPD: Test Time Model Pruning and Distillation","created":"2024-12-10","cited_by_count":0,"area":null},{"id":"2502.06034","title":"Traveling Waves Integrate Spatial Information Through Time","created":"2025-02-09","cited_by_count":0,"area":null},{"id":"2502.19692","title":"A Residual Multi-task Network for Joint Classification and Regression in Medical Imaging","created":"2025-02-27","cited_by_count":0,"area":null},{"id":"2510.11963","title":"QLENS: Towards A Quantum Perspective of Language Transformers","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2512.23837","title":"Adversarial Lens: Exploiting Attention Layers to Generate Adversarial Examples for Evaluation","created":"2025-12-29","cited_by_count":0,"area":"mechinterp"},{"id":"2603.26756","title":"GradAttn: Replacing Fixed Residual Connections with Task-Modulated Attention Pathways","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2605.27033","title":"Tracing Computation Density in LLMs","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2606.16112","title":"Scaling Adaptive Depth with Norm-Agnostic Residual Networks","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2607.15693","title":"Toward a mechanistic understanding of inference in visual cortex and diffusion models","created":"2026-07-17","cited_by_count":0,"area":"diffusion"},{"id":"2608.29706","title":"The Depth Flow of Token Representations Is Nonlinear and Does Not Descend Its Own Density","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.31098","title":"The Residual Stream's Effective Depth","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2610.04130","title":"Shared Geometry Is Not Shared Physics: A Layerwise Test of the Platonic Representation Hypothesis in Astronomy","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04751","title":"Dynamic Routing as a New Dimension for Test-time Versatility of LLMs","created":"2026-10-03","cited_by_count":0,"area":"lr"},{"id":"2610.19814","title":"When Does Depth Help? Understanding Layerwise Inference in Tabular Foundation Models","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}