{"list":"other","total":57,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2203.07814","title":"Competition-Level Code Generation with AlphaCode","created":"2022-02-08","cited_by_count":1462},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"2305.04388","title":"Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting","created":"2023-05-07","cited_by_count":1122},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"2203.05794","title":"BERTopic: Neural topic modeling with a class-based TF-IDF procedure","created":"2022-03-11","cited_by_count":801},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723},{"id":"2412.08905","title":"Phi-4 Technical Report","created":"2024-12-12","cited_by_count":711},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"2406.04093","title":"Scaling and evaluating sparse autoencoders","created":"2024-06-06","cited_by_count":553},{"id":"1812.01193","title":"e-SNLI: Natural Language Inference with Natural Language Explanations","created":"2018-12-04","cited_by_count":468},{"id":"2408.05147","title":"Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2","created":"2024-08-09","cited_by_count":394},{"id":"2501.16496","title":"Open Problems in Mechanistic Interpretability","created":"2025-01-27","cited_by_count":179},{"id":"2006.14032","title":"Compositional Explanations of Neurons","created":"2020-06-24","cited_by_count":172},{"id":"2004.02105","title":"Unsupervised Domain Clusters in Pretrained Language Models","created":"2020-04-05","cited_by_count":160},{"id":"2410.20526","title":"Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders","created":"2024-10-27","cited_by_count":143},{"id":"2006.03589","title":"Higher-Order Explanations of Graph Neural Networks via Relevant Walks","created":"2020-06-05","cited_by_count":138},{"id":"2410.13928","title":"Automatically Interpreting Millions of Features in Large Language Models","created":"2024-10-17","cited_by_count":113},{"id":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101},{"id":"2202.07304","title":"XAI for Transformers: Better Explanations through Conservative Propagation","created":"2022-02-15","cited_by_count":100},{"id":"2104.07143","title":"An Interpretability Illusion for BERT","created":"2021-04-14","cited_by_count":97},{"id":"2310.11207","title":"Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations","created":"2023-10-17","cited_by_count":90},{"id":"2407.12831","title":"Truth is Universal: Robust Detection of Lies in LLMs","created":"2024-07-03","cited_by_count":79},{"id":"2404.12259","title":"Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM","created":"2024-04-18","cited_by_count":78},{"id":"2210.01892","title":"Polysemanticity and Capacity in Neural Networks","created":"2022-10-04","cited_by_count":77},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62},{"id":"2305.13749","title":"Goal-Driven Explainable Clustering via Language Descriptions","created":"2023-05-23","cited_by_count":58},{"id":"2310.04276","title":"From task structures to world models: What do LLMs know?","created":"2023-10-06","cited_by_count":46},{"id":"2309.10312","title":"Rigorously Assessing Natural Language Explanations of Neurons","created":"2023-09-19","cited_by_count":45},{"id":"2501.08319","title":"Enhancing Automated Interpretability with Output-Centric Feature Descriptions","created":"2025-01-14","cited_by_count":41},{"id":"1906.07633","title":"From Clustering to Cluster Explanations via Neural Networks","created":"2019-06-18","cited_by_count":34},{"id":"2003.05431","title":"Building and Interpreting Deep Similarity Models","created":"2020-03-11","cited_by_count":34},{"id":"2311.13594","title":"Labeling Neural Representations with Inverse Recognition","created":"2023-11-22","cited_by_count":32},{"id":"2004.14096","title":"Do Neural Language Models Show Preferences for Syntactic Formalisms?","created":"2020-04-29","cited_by_count":30},{"id":"2501.05398","title":"Mechanistic understanding and validation of large AI models with SemanticLens","created":"2025-01-09","cited_by_count":29},{"id":"2402.14897","title":"Chain-of-Thought Unfaithfulness as Disguised Accuracy","created":"2024-02-22","cited_by_count":28},{"id":"2212.14855","title":"Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces","created":"2022-12-30","cited_by_count":25},{"id":"2401.17975","title":"Understanding polysemanticity in neural networks through coding theory","created":"2024-01-31","cited_by_count":17},{"id":"2405.20331","title":"CoSy: Evaluating Textual Explanations of Neurons","created":"2024-05-30","cited_by_count":17},{"id":"2305.01020","title":"Evaluating statistical language models as pragmatic reasoners","created":"2023-05-01","cited_by_count":15},{"id":"2206.04530","title":"DORA: Exploring Outlier Representations in Deep Neural Networks","created":"2022-06-09","cited_by_count":14},{"id":"2404.12545","title":"Latent Concept-based Explanation of NLP Models","created":"2024-04-18","cited_by_count":13},{"id":"2502.16994","title":"FADE: Why Bad Descriptions Happen to Good Features","created":"2025-02-24","cited_by_count":13},{"id":"2310.06200","title":"The Importance of Prompt Tuning for Automated Neuron Explanations","created":"2023-10-09","cited_by_count":12},{"id":"2310.13439","title":"Self-Consistency of Large Language Models under Ambiguity","created":"2023-10-20","cited_by_count":12},{"id":"2402.15055","title":"Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions","created":"2024-02-23","cited_by_count":12},{"id":"2405.06604","title":"Explaining Text Similarity in Transformer Models","created":"2024-05-10","cited_by_count":9},{"id":"2501.05855","title":"ConSim: Measuring Concept-Based Explanations' Effectiveness with Automated Simulatability","created":"2025-01-10","cited_by_count":9},{"id":"2504.07965","title":"Cat, Rat, Meow: On the Alignment of Language Model and Human Term-Similarity Judgments","created":"2025-04-10","cited_by_count":1}],"next_cursor":null}