{"list":"other","total":78,"rows":[{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"1412.6806","title":"Striving for Simplicity: The All Convolutional Net","created":"2014-12-21","cited_by_count":990},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"1710.10547","title":"Interpretation of Neural Networks is Fragile","created":"2017-10-29","cited_by_count":444},{"id":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300},{"id":"2405.14860","title":"Not All Language Model Features Are One-Dimensionally Linear","created":"2024-05-23","cited_by_count":212},{"id":"2501.16496","title":"Open Problems in Mechanistic Interpretability","created":"2025-01-27","cited_by_count":179},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178},{"id":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159},{"id":"2412.06410","title":"BatchTopK Sparse Autoencoders","created":"2024-12-09","cited_by_count":130},{"id":"2006.15417","title":"Invertible Concept-based Explanations for CNN Models with Non-negative Concept Activation Vectors","created":"2020-06-27","cited_by_count":120},{"id":"2106.02666","title":"Counterfactual Explanations Can Be Manipulated","created":"2021-06-04","cited_by_count":113},{"id":"2306.07304","title":"A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation","created":"2023-06-11","cited_by_count":109},{"id":"1602.03616","title":"Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks","created":"2016-02-11","cited_by_count":106},{"id":"2112.04417","title":"What I Cannot Predict, I Do Not Understand: A Human-Centered Evaluation Framework for Explainability Methods","created":"2021-12-06","cited_by_count":98},{"id":"1709.02508","title":"Deep Subspace Clustering Networks","created":"2017-09-08","cited_by_count":94},{"id":"2105.14944","title":"The effectiveness of feature attribution methods and its correlation with automatic evaluation scores","created":"2021-05-31","cited_by_count":88},{"id":"2106.00786","title":"The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations","created":"2021-06-01","cited_by_count":87},{"id":"2502.00873","title":"Language Models Use Trigonometry to Do Addition","created":"2025-02-02","cited_by_count":70},{"id":"1904.08939","title":"Understanding Neural Networks via Feature Visualization: A survey","created":"2019-04-18","cited_by_count":65},{"id":"2111.04138","title":"Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis","created":"2021-11-07","cited_by_count":65},{"id":"1710.06487","title":"Classification and Geometry of General Perceptual Manifolds","created":"2017-10-17","cited_by_count":62},{"id":"2502.03714","title":"Universal Sparse Autoencoders: Interpretable Cross-Model Concept Alignment","created":"2025-02-06","cited_by_count":62},{"id":"2503.01822","title":"Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry","created":"2025-03-03","cited_by_count":61},{"id":"2104.07059","title":"Neural population geometry: An approach for understanding biological and artificial neural networks","created":"2021-04-14","cited_by_count":52},{"id":"2006.00442","title":"Evaluations and Methods for Explanation through Robustness Analysis","created":"2020-05-31","cited_by_count":51},{"id":"2505.18235","title":"The Origins of Representation Manifolds in Large Language Models","created":"2025-05-23","cited_by_count":51},{"id":"1507.01238","title":"Scalable Sparse Subspace Clustering by Orthogonal Matching Pursuit","created":"2015-07-05","cited_by_count":50},{"id":"2301.11911","title":"Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees","created":"2023-01-27","cited_by_count":50},{"id":"2506.03093","title":"From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit","created":"2025-06-03","cited_by_count":49},{"id":"1411.3230","title":"Sparse Modeling for Image and Vision Processing","created":"2014-11-12","cited_by_count":48},{"id":"2601.04480","title":"When Models Manipulate Manifolds: The Geometry of a Counting Task","created":"2026-01-08","cited_by_count":46},{"id":"2201.10000","title":"Neural Manifold Clustering and Embedding","created":"2022-01-24","cited_by_count":44},{"id":"2406.03445","title":"Pre-trained Large Language Models Use Fourier Features to Compute Addition","created":"2024-06-05","cited_by_count":39},{"id":"2406.08074","title":"A Concept-Based Explainability Framework for Large Multimodal Models","created":"2024-06-12","cited_by_count":39},{"id":"2410.08201","title":"Efficient Dictionary Learning with Switch Sparse Autoencoders","created":"2024-10-10","cited_by_count":39},{"id":"2406.03662","title":"The Missing Curve Detectors of InceptionV1: Applying Sparse Autoencoders to InceptionV1 Early Vision","created":"2024-06-06","cited_by_count":37},{"id":"2510.08638","title":"Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry","created":"2025-10-08","cited_by_count":34},{"id":"2604.28119","title":"Do Sparse Autoencoders Capture Concept Manifolds?","created":"2026-04-30","cited_by_count":31},{"id":"2306.06805","title":"Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization","created":"2023-06-11","cited_by_count":27},{"id":"1610.05211","title":"Structured Sparse Subspace Clustering: A Joint Affinity Learning and Subspace Clustering Framework","created":"2016-10-17","cited_by_count":26},{"id":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26},{"id":"2511.01836","title":"Priors in Time: Missing Inductive Biases for Language Model Interpretability","created":"2025-11-03","cited_by_count":25},{"id":"1301.2603","title":"Robust subspace clustering","created":"2013-01-11","cited_by_count":24},{"id":"2602.15029","title":"Symmetry in language statistics shapes the geometry of model representations","created":"2026-02-16","cited_by_count":24},{"id":"2401.10831","title":"Understanding Video Transformers via Universal Concept Discovery","created":"2024-01-19","cited_by_count":23},{"id":"2410.11179","title":"Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations with MDL-SAEs","created":"2024-10-15","cited_by_count":23},{"id":"2404.02233","title":"Visual Concept Connectome (VCC): Open World Concept Discovery and their Interlayer Connections in Deep Models","created":"2024-04-02","cited_by_count":22},{"id":"2502.09741","title":"FoNE: Precise Single-Token Number Embeddings via Fourier Features","created":"2025-02-13","cited_by_count":22},{"id":"2511.05541","title":"Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability","created":"2025-10-30","cited_by_count":18},{"id":"2506.15679","title":"Dense SAE Latents Are Features, Not Bugs","created":"2025-06-18","cited_by_count":17},{"id":"2503.01824","title":"From superposition to sparse codes: interpretable representations in neural networks","created":"2025-03-03","cited_by_count":16},{"id":"2602.02315","title":"The Shape of Beliefs: Geometry, Dynamics, and Interventions along Representation Manifolds of Language Models' Posteriors","created":"2026-02-02","cited_by_count":15},{"id":"2602.02464","title":"From Directions to Regions: Decomposing Activations in Language Models via Local Geometry","created":"2026-02-02","cited_by_count":12},{"id":"2509.02565","title":"Understanding sparse autoencoder scaling in the presence of feature manifolds","created":"2025-09-02","cited_by_count":11},{"id":"2602.15293","title":"The Information Geometry of Softmax: Probing and Steering","created":"2026-02-17","cited_by_count":11},{"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},{"id":"2310.11431","title":"Identifying Interpretable Visual Features in Artificial and Biological Neural Systems","created":"2023-10-17","cited_by_count":9},{"id":"2510.00404","title":"AbsTopK: Rethinking Sparse Autoencoders For Bidirectional Features","created":"2025-10-01","cited_by_count":9},{"id":"2104.00145","title":"The population doctrine in cognitive neuroscience","created":"2021-03-31","cited_by_count":7},{"id":"2305.17154","title":"On convex decision regions in deep network representations","created":"2023-05-26","cited_by_count":7},{"id":"2604.20817","title":"Convergent Evolution: How Different Language Models Learn Similar Number Representations","created":"2026-04-22","cited_by_count":6},{"id":"1612.03450","title":"Noisy subspace clustering via matching pursuits","created":"2016-12-11","cited_by_count":5},{"id":"2606.06333","title":"Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability","created":"2026-06-04","cited_by_count":4},{"id":"2102.07003","title":"On the convergence of group-sparse autoencoders","created":"2021-02-13","cited_by_count":3},{"id":"2512.14884","title":"Vibe Spaces for Creatively Connecting and Expressing Visual Concepts","created":"2025-12-16","cited_by_count":3},{"id":"2511.05745","title":"Beyond Redundancy: Diverse and Specialized Multi-Expert Sparse Autoencoder","created":"2025-11-07","cited_by_count":1},{"id":"2605.09224","title":"SMIXAE: Towards Unsupervised Manifold Discovery in Language Models","created":"2026-05-09","cited_by_count":1}],"next_cursor":null}