{"list":"other","total":198,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2204.05862","title":"Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback","created":"2022-04-12","cited_by_count":3720},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"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":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"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":"1706.03825","title":"SmoothGrad: removing noise by adding noise","created":"2017-06-12","cited_by_count":1109},{"id":"2210.07229","title":"Mass-Editing Memory in a Transformer","created":"2022-10-13","cited_by_count":1001},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2308.10248","title":"Steering Language Models With Activation Engineering","created":"2023-08-20","cited_by_count":922},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"2311.03658","title":"The Linear Representation Hypothesis and the Geometry of Large Language Models","created":"2023-11-07","cited_by_count":716},{"id":"2310.06824","title":"The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets","created":"2023-10-10","cited_by_count":712},{"id":"2307.13702","title":"Measuring Faithfulness in Chain-of-Thought Reasoning","created":"2023-07-17","cited_by_count":703},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"2211.15661","title":"What learning algorithm is in-context learning? Investigations with linear models","created":"2022-11-28","cited_by_count":684},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623},{"id":"2009.07896","title":"Captum: A unified and generic model interpretability library for PyTorch","created":"2020-09-16","cited_by_count":547},{"id":"2110.11309","title":"Fast Model Editing at Scale","created":"2021-10-21","cited_by_count":498},{"id":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447},{"id":"1905.06316","title":"What do you learn from context? Probing for sentence structure in contextualized word representations","created":"2019-05-15","cited_by_count":438},{"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":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422},{"id":"2309.12288","title":"The Reversal Curse: LLMs trained on \"A is B\" fail to learn \"B is A\"","created":"2023-09-21","cited_by_count":407},{"id":"2309.03883","title":"DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models","created":"2023-09-07","cited_by_count":376},{"id":"2309.16042","title":"Towards Best Practices of Activation Patching in Language Models: Metrics and Methods","created":"2023-09-27","cited_by_count":359},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334},{"id":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"2402.03744","title":"INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection","created":"2024-02-06","cited_by_count":323},{"id":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316},{"id":"2310.15916","title":"In-Context Learning Creates Task Vectors","created":"2023-10-24","cited_by_count":312},{"id":"2402.17762","title":"Massive Activations in Large Language Models","created":"2024-02-27","cited_by_count":294},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"2306.03819","title":"LEACE: Perfect linear concept erasure in closed form","created":"2023-06-06","cited_by_count":267},{"id":"2301.04213","title":"Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models","created":"2023-01-10","cited_by_count":243},{"id":"2401.06102","title":"Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models","created":"2024-01-11","cited_by_count":235},{"id":"2404.15574","title":"Retrieval Head Mechanistically Explains Long-Context Factuality","created":"2024-04-24","cited_by_count":232},{"id":"1612.08220","title":"Understanding Neural Networks through Representation Erasure","created":"2016-12-24","cited_by_count":224},{"id":"2404.15255","title":"How to use and interpret activation patching","created":"2024-04-23","cited_by_count":214},{"id":"2303.02536","title":"Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations","created":"2023-03-05","cited_by_count":209},{"id":"2310.10348","title":"Attribution Patching Outperforms Automated Circuit Discovery","created":"2023-10-16","cited_by_count":209},{"id":"2207.04901","title":"Exploring Length Generalization in Large Language Models","created":"2022-07-11","cited_by_count":206},{"id":"2307.03987","title":"A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generation","created":"2023-07-08","cited_by_count":206},{"id":"2301.04709","title":"Causal Abstraction: A Theoretical Foundation for Mechanistic Interpretability","created":"2023-01-11","cited_by_count":205},{"id":"2305.00586","title":"How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model","created":"2023-04-30","cited_by_count":202},{"id":"2308.09124","title":"Linearity of Relation Decoding in Transformer Language Models","created":"2023-08-17","cited_by_count":200},{"id":"2310.16028","title":"What Algorithms can Transformers Learn? A Study in Length Generalization","created":"2023-10-24","cited_by_count":199},{"id":"2304.05969","title":"Localizing Model Behavior with Path Patching","created":"2023-04-12","cited_by_count":195},{"id":"2310.16218","title":"Knowledge Editing for Large Language Models: A Survey","created":"2023-10-24","cited_by_count":194},{"id":"2106.06981","title":"Thinking Like Transformers","created":"2021-06-13","cited_by_count":184},{"id":"1605.09304","title":"Synthesizing the preferred inputs for neurons in neural networks via deep generator networks","created":"2016-05-30","cited_by_count":181},{"id":"1412.6856","title":"Object Detectors Emerge in Deep Scene CNNs","created":"2014-12-22","cited_by_count":179},{"id":"2404.16014","title":"Improving Dictionary Learning with Gated Sparse Autoencoders","created":"2024-04-24","cited_by_count":179},{"id":"2310.15154","title":"Linear Representations of Sentiment in Large Language Models","created":"2023-10-23","cited_by_count":163},{"id":"2306.00802","title":"Birth of a Transformer: A Memory Viewpoint","created":"2023-06-01","cited_by_count":161},{"id":"1702.08591","title":"The Shattered Gradients Problem: If resnets are the answer, then what is the question?","created":"2017-02-28","cited_by_count":157},{"id":"2306.17844","title":"The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks","created":"2023-06-30","cited_by_count":156},{"id":"2307.15771","title":"The Hydra Effect: Emergent Self-repair in Language Model Computations","created":"2023-07-28","cited_by_count":156},{"id":"2306.12929","title":"Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing","created":"2023-06-22","cited_by_count":151},{"id":"2307.09458","title":"Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla","created":"2023-07-18","cited_by_count":149},{"id":"2402.14811","title":"Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking","created":"2024-02-22","cited_by_count":149},{"id":"2403.17806","title":"Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms","created":"2024-03-26","cited_by_count":149},{"id":"1704.01444","title":"Learning to Generate Reviews and Discovering Sentiment","created":"2017-04-05","cited_by_count":148},{"id":"2011.05429","title":"Debugging Tests for Model Explanations","created":"2020-11-10","cited_by_count":147},{"id":"2102.13019","title":"Investigating the Limitations of Transformers with Simple Arithmetic Tasks","created":"2021-02-25","cited_by_count":139},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129},{"id":"2401.14446","title":"Black-Box Access is Insufficient for Rigorous AI Audits","created":"2024-01-25","cited_by_count":126}],"next_cursor":"100"}