{"list":"other","total":72,"rows":[{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"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":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"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":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"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":"2212.03827","title":"Discovering Latent Knowledge in Language Models Without Supervision","created":"2022-12-07","cited_by_count":767},{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623},{"id":"2104.08696","title":"Knowledge Neurons in Pretrained Transformers","created":"2021-04-18","cited_by_count":601},{"id":"2203.14680","title":"Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space","created":"2022-03-28","cited_by_count":532},{"id":"2310.06694","title":"Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning","created":"2023-10-10","cited_by_count":415},{"id":"2305.01610","title":"Finding Neurons in a Haystack: Case Studies with Sparse Probing","created":"2023-05-02","cited_by_count":334},{"id":"1806.05759","title":"Insights on representational similarity in neural networks with canonical correlation","created":"2018-06-14","cited_by_count":324},{"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":"2310.15213","title":"Function Vectors in Large Language Models","created":"2023-10-23","cited_by_count":308},{"id":"2209.00626","title":"The Alignment Problem from a Deep Learning Perspective","created":"2022-08-30","cited_by_count":258},{"id":"2009.05041","title":"Understanding the Role of Individual Units in a Deep Neural Network","created":"2020-09-10","cited_by_count":255},{"id":"2306.12001","title":"An Overview of Catastrophic AI Risks","created":"2023-06-21","cited_by_count":222},{"id":"1605.09096","title":"Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change","created":"2016-05-30","cited_by_count":221},{"id":"1511.07543","title":"Convergent Learning: Do different neural networks learn the same representations?","created":"2015-11-24","cited_by_count":220},{"id":"2106.07682","title":"Revisiting Model Stitching to Compare Neural Representations","created":"2021-06-14","cited_by_count":209},{"id":"2006.14032","title":"Compositional Explanations of Neurons","created":"2020-06-24","cited_by_count":172},{"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":"1704.01444","title":"Learning to Generate Reviews and Discovering Sentiment","created":"2017-04-05","cited_by_count":148},{"id":"2209.02535","title":"Analyzing Transformers in Embedding Space","created":"2022-09-06","cited_by_count":132},{"id":"2305.06329","title":"Similarity of Neural Network Models: A Survey of Functional and Representational Measures","created":"2023-05-10","cited_by_count":131},{"id":"1812.09355","title":"What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models","created":"2018-12-21","cited_by_count":124},{"id":"2110.14739","title":"Generalized Shape Metrics on Neural Representations","created":"2021-10-27","cited_by_count":112},{"id":"1811.01157","title":"Identifying and Controlling Important Neurons in Neural Machine Translation","created":"2018-11-03","cited_by_count":111},{"id":"1807.07814","title":"Interactive Supercomputing on 40,000 Cores for Machine Learning and Data Analysis","created":"2018-07-20","cited_by_count":110},{"id":"2310.17191","title":"How do Language Models Bind Entities in Context?","created":"2023-10-26","cited_by_count":108},{"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":"2311.08379","title":"Scheming AIs: Will AIs fake alignment during training in order to get power?","created":"2023-11-14","cited_by_count":97},{"id":"2309.04827","title":"Neurons in Large Language Models: Dead, N-gram, Positional","created":"2023-09-09","cited_by_count":88},{"id":"1710.04773","title":"Residual Connections Encourage Iterative Inference","created":"2017-10-13","cited_by_count":77},{"id":"2312.09230","title":"Successor Heads: Recurring, Interpretable Attention Heads In The Wild","created":"2023-12-14","cited_by_count":77},{"id":"2310.04625","title":"Copy Suppression: Comprehensively Understanding an Attention Head","created":"2023-10-06","cited_by_count":76},{"id":"2201.00058","title":"Representation Topology Divergence: A Method for Comparing Neural Network Representations","created":"2021-12-31","cited_by_count":66},{"id":"2211.07349","title":"Finding Skill Neurons in Pre-trained Transformer-based Language Models","created":"2022-11-14","cited_by_count":66},{"id":"2205.14258","title":"On the Symmetries of Deep Learning Models and their Internal Representations","created":"2022-05-27","cited_by_count":64},{"id":"1810.11750","title":"Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation","created":"2018-10-28","cited_by_count":62},{"id":"2110.07483","title":"On the Pitfalls of Analyzing Individual Neurons in Language Models","created":"2021-10-14","cited_by_count":62},{"id":"1802.02664","title":"Geometry Score: A Method For Comparing Generative Adversarial Networks","created":"2018-02-07","cited_by_count":57},{"id":"2310.17688","title":"Managing extreme AI risks amid rapid progress","created":"2023-10-26","cited_by_count":48},{"id":"2306.09346","title":"Rosetta Neurons: Mining the Common Units in a Model Zoo","created":"2023-06-15","cited_by_count":46},{"id":"2309.10312","title":"Rigorously Assessing Natural Language Explanations of Neurons","created":"2023-09-19","cited_by_count":45},{"id":"2206.13289","title":"Analyzing Encoded Concepts in Transformer Language Models","created":"2022-06-27","cited_by_count":38},{"id":"2305.02582","title":"On the Expressivity Role of LayerNorm in Transformers' Attention","created":"2023-05-04","cited_by_count":33},{"id":"2108.01661","title":"Grounding Representation Similarity with Statistical Testing","created":"2021-08-03","cited_by_count":29},{"id":"2111.12485","title":"Understanding the Dynamics of DNNs Using Graph Modularity","created":"2021-11-24","cited_by_count":26},{"id":"2206.08347","title":"Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning","created":"2022-06-16","cited_by_count":20},{"id":"2312.10091","title":"Look Before You Leap: A Universal Emergent Decomposition of Retrieval Tasks in Language Models","created":"2023-12-13","cited_by_count":18},{"id":"2210.06545","title":"GULP: a prediction-based metric between representations","created":"2022-10-12","cited_by_count":17},{"id":"2211.11665","title":"Representational dissimilarity metric spaces for stochastic neural networks","created":"2022-11-21","cited_by_count":17},{"id":"2003.11498","title":"Similarity of Neural Networks with Gradients","created":"2020-03-25","cited_by_count":16},{"id":"2004.05107","title":"Levels of Analysis for Machine Learning","created":"2020-04-06","cited_by_count":11},{"id":"2203.11815","title":"Clustering units in neural networks: upstream vs downstream information","created":"2022-03-22","cited_by_count":11},{"id":"1912.04783","title":"Frivolous Units: Wider Networks Are Not Really That Wide","created":"2019-12-10","cited_by_count":10},{"id":"2012.03793","title":"Inter-layer Information Similarity Assessment of Deep Neural Networks Via Topological Similarity and Persistence Analysis of Data Neighbour Dynamics","created":"2020-12-07","cited_by_count":7},{"id":"2311.00863","title":"Training Dynamics of Contextual N-Grams in Language Models","created":"2023-11-01","cited_by_count":7},{"id":"2203.05488","title":"Geometric and Topological Inference for Deep Representations of Complex Networks","created":"2022-03-10","cited_by_count":4}],"next_cursor":null}