{"list":"other","total":62,"rows":[{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2402.04249","title":"HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal","created":"2024-02-06","cited_by_count":1429},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"2403.03218","title":"The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning","created":"2024-03-05","cited_by_count":509},{"id":"2403.19647","title":"Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models","created":"2024-03-28","cited_by_count":435},{"id":"1901.09451","title":"Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting","created":"2019-01-27","cited_by_count":349},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334},{"id":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300},{"id":"2403.03952","title":"Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders","created":"2024-03-06","cited_by_count":224},{"id":"2501.17148","title":"AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders","created":"2025-01-28","cited_by_count":218},{"id":"2405.14860","title":"Not All Language Model Features Are One-Dimensionally Linear","created":"2024-05-23","cited_by_count":212},{"id":"2103.12828","title":"Learning to Optimize: A Primer and A Benchmark","created":"2021-03-23","cited_by_count":208},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178},{"id":"1601.03764","title":"Linear Algebraic Structure of Word Senses, with Applications to Polysemy","created":"2016-01-14","cited_by_count":165},{"id":"2409.14507","title":"A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders","created":"2024-09-22","cited_by_count":160},{"id":"2412.06410","title":"BatchTopK Sparse Autoencoders","created":"2024-12-09","cited_by_count":130},{"id":"2503.09532","title":"SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability","created":"2025-03-12","cited_by_count":124},{"id":"2502.16681","title":"Are Sparse Autoencoders Useful? A Case Study in Sparse Probing","created":"2025-02-23","cited_by_count":115},{"id":"2412.12101","title":"InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders","created":"2024-11-13","cited_by_count":66},{"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":"2410.19278","title":"Applying sparse autoencoders to unlearn knowledge in language models","created":"2024-10-25","cited_by_count":59},{"id":"2408.10920","title":"Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations","created":"2024-08-20","cited_by_count":47},{"id":"2410.14670","title":"Decomposing The Dark Matter of Sparse Autoencoders","created":"2024-10-18","cited_by_count":45},{"id":"1503.00778","title":"Simple, Efficient, and Neural Algorithms for Sparse Coding","created":"2015-03-02","cited_by_count":37},{"id":"2405.13967","title":"Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity","created":"2024-05-22","cited_by_count":35},{"id":"2409.04478","title":"Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small","created":"2024-09-05","cited_by_count":34},{"id":"2411.04430","title":"Towards Unifying Interpretability and Control: Evaluation via Intervention","created":"2024-11-07","cited_by_count":32},{"id":"2302.11068","title":"Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time","created":"2023-02-21","cited_by_count":31},{"id":"2501.17727","title":"Automated Interpretability Metrics Do Not Distinguish Trained and Random Transformers","created":"2025-01-29","cited_by_count":30},{"id":"1601.02049","title":"A note on the sample complexity of the Er-SpUD algorithm by Spielman, Wang and Wright for exact recovery of sparsely used dictionaries","created":"2016-01-08","cited_by_count":26},{"id":"2505.20322","title":"Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms","created":"2025-05-23","cited_by_count":24},{"id":"2208.06671","title":"Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes","created":"2022-08-13","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":"1407.1543","title":"Dictionary Learning and Tensor Decomposition via the Sum-of-Squares Method","created":"2014-07-06","cited_by_count":22},{"id":"2406.04331","title":"PaCE: Parsimonious Concept Engineering for Large Language Models","created":"2024-06-06","cited_by_count":19},{"id":"2506.23845","title":"Position: Use Sparse Autoencoders to Discover Unknowns","created":"2025-06-30","cited_by_count":19},{"id":"2411.13117","title":"Compute Optimal Inference and Provable Amortisation Gap in Sparse Autoencoders","created":"2024-11-20","cited_by_count":18},{"id":"2410.11767","title":"Analyzing (In)Abilities of SAEs via Formal Languages","created":"2024-10-15","cited_by_count":17},{"id":"2502.09135","title":"Interpreting and Steering Protein Language Models through Sparse Autoencoders","created":"2025-02-13","cited_by_count":17},{"id":"2106.00058","title":"Stable and Interpretable Unrolled Dictionary Learning","created":"2021-05-31","cited_by_count":15},{"id":"2411.18895","title":"Evaluating Sparse Autoencoders on Targeted Concept Erasure Tasks","created":"2024-11-28","cited_by_count":15},{"id":"1609.00285","title":"Understanding Trainable Sparse Coding via Matrix Factorization","created":"2016-09-01","cited_by_count":12},{"id":"2106.06338","title":"Understanding approximate and unrolled dictionary learning for pattern recovery","created":"2021-06-11","cited_by_count":11},{"id":"1809.10313","title":"Efficient Dictionary Learning with Gradient Descent","created":"2018-09-27","cited_by_count":10},{"id":"2002.07898","title":"Deep Transform and Metric Learning Network: Wedding Deep Dictionary Learning and Neural Networks","created":"2020-02-18","cited_by_count":6},{"id":"2506.12217","title":"From Emergence to Control: Probing and Modulating Self-Reflection in Language Models","created":"2025-06-13","cited_by_count":6},{"id":"2411.03993","title":"Choosing the right basis for interpretability: Psychophysical comparison between neuron-based and dictionary-based representations","created":"2024-11-06","cited_by_count":5},{"id":"1711.03634","title":"Alternating minimization for dictionary learning: Local Convergence Guarantees","created":"2017-11-09","cited_by_count":4},{"id":"2502.01048","title":"Sparks of Explainability: Recent Advancements in Explaining Large Vision Models","created":"2025-02-03","cited_by_count":4},{"id":"1406.1943","title":"Structured Dictionary Learning for Classification","created":"2014-06-08","cited_by_count":1},{"id":"2009.01379","title":"Soft thresholding schemes for multiple signal classification algorithm","created":"2020-09-02","cited_by_count":1},{"id":"2011.10100","title":"Efficient Consensus Model based on Proximal Gradient Method applied to Convolutional Sparse Problems","created":"2020-11-19","cited_by_count":1},{"id":"2407.06646","title":"Variational Learning ISTA","created":"2024-07-09","cited_by_count":1}],"next_cursor":null}