{"list":"other","total":114,"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":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"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":"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":"2306.03341","title":"Inference-Time Intervention: Eliciting Truthful Answers from a Language Model","created":"2023-06-06","cited_by_count":1302},{"id":"1411.1792","title":"How transferable are features in deep neural networks?","created":"2014-11-06","cited_by_count":1225},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2406.11717","title":"Refusal in Language Models Is Mediated by a Single Direction","created":"2024-06-17","cited_by_count":1032},{"id":"2005.04118","title":"Beyond Accuracy: Behavioral Testing of NLP models with CheckList","created":"2020-05-08","cited_by_count":1006},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"id":"1412.6806","title":"Striving for Simplicity: The All Convolutional Net","created":"2014-12-21","cited_by_count":990},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1909.00512","title":"How Contextual are Contextualized Word Representations? Comparing the Geometry of BERT, ELMo, and GPT-2 Embeddings","created":"2019-09-02","cited_by_count":784},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"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":"1909.03368","title":"Designing and Interpreting Probes with Control Tasks","created":"2019-09-08","cited_by_count":640},{"id":"1908.04626","title":"Attention is not not Explanation","created":"2019-08-13","cited_by_count":636},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"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":"1710.10547","title":"Interpretation of Neural Networks is Fragile","created":"2017-10-29","cited_by_count":444},{"id":"1911.02508","title":"Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods","created":"2019-11-06","cited_by_count":443},{"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":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"1611.01368","title":"Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies","created":"2016-11-04","cited_by_count":354},{"id":"1908.08593","title":"Revealing the Dark Secrets of BERT","created":"2019-08-21","cited_by_count":301},{"id":"2407.14435","title":"Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders","created":"2024-07-19","cited_by_count":300},{"id":"1606.04155","title":"Rationalizing Neural Predictions","created":"2016-06-13","cited_by_count":281},{"id":"2003.12298","title":"Information-Theoretic Probing with Minimum Description Length","created":"2020-03-27","cited_by_count":232},{"id":"1608.04207","title":"Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks","created":"2016-08-15","cited_by_count":216},{"id":"1906.02715","title":"Visualizing and Measuring the Geometry of BERT","created":"2019-06-06","cited_by_count":216},{"id":"2303.02536","title":"Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations","created":"2023-03-05","cited_by_count":209},{"id":"1506.01066","title":"Visualizing and Understanding Neural Models in NLP","created":"2015-06-02","cited_by_count":200},{"id":"2106.06981","title":"Thinking Like Transformers","created":"2021-06-13","cited_by_count":184},{"id":"2006.14032","title":"Compositional Explanations of Neurons","created":"2020-06-24","cited_by_count":172},{"id":"1702.04595","title":"Visualizing Deep Neural Network Decisions: Prediction Difference Analysis","created":"2017-02-15","cited_by_count":166},{"id":"1704.03471","title":"What do Neural Machine Translation Models Learn about Morphology?","created":"2017-04-11","cited_by_count":166},{"id":"1506.02078","title":"Visualizing and Understanding Recurrent Networks","created":"2015-06-05","cited_by_count":160},{"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":"2205.10487","title":"Scaling Laws and Interpretability of Learning from Repeated Data","created":"2022-05-21","cited_by_count":152},{"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":"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":"2106.16213","title":"Saturated Transformers are Constant-Depth Threshold Circuits","created":"2021-06-30","cited_by_count":139},{"id":"2102.12060","title":"Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing","created":"2021-02-24","cited_by_count":126},{"id":"2112.08674","title":"Reframing Human-AI Collaboration for Generating Free-Text Explanations","created":"2021-12-16","cited_by_count":125},{"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":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124},{"id":"1805.04908","title":"On the Practical Computational Power of Finite Precision RNNs for Language Recognition","created":"2018-05-13","cited_by_count":117},{"id":"1908.04211","title":"On Identifiability in Transformers","created":"2019-08-12","cited_by_count":116},{"id":"1902.02041","title":"Fooling Neural Network Interpretations via Adversarial Model Manipulation","created":"2019-02-06","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":"2403.00745","title":"AtP*: An efficient and scalable method for localizing LLM behaviour to components","created":"2024-03-01","cited_by_count":111},{"id":"1808.08079","title":"Under the Hood: Using Diagnostic Classifiers to Investigate and Improve how Language Models Track Agreement Information","created":"2018-08-24","cited_by_count":97},{"id":"2010.02695","title":"Analyzing Individual Neurons in Pre-trained Language Models","created":"2020-10-06","cited_by_count":97},{"id":"2104.07143","title":"An Interpretability Illusion for BERT","created":"2021-04-14","cited_by_count":97},{"id":"2403.00824","title":"Information Flow Routes: Automatically Interpreting Language Models at Scale","created":"2024-02-27","cited_by_count":95},{"id":"1903.07435","title":"The emergence of number and syntax units in LSTM language models","created":"2019-03-18","cited_by_count":94},{"id":"1911.12246","title":"Do Attention Heads in BERT Track Syntactic Dependencies?","created":"2019-11-27","cited_by_count":88},{"id":"2210.16156","title":"Reliability of CKA as a Similarity Measure in Deep Learning","created":"2022-10-28","cited_by_count":87},{"id":"2303.11873","title":"A Tale of Two Circuits: Grokking as Competition of Sparse and Dense Subnetworks","created":"2023-03-21","cited_by_count":83},{"id":"2108.13138","title":"Neuron-level Interpretation of Deep NLP Models: A Survey","created":"2021-08-30","cited_by_count":81},{"id":"2006.01067","title":"Aligning Faithful Interpretations with their Social Attribution","created":"2020-06-01","cited_by_count":79},{"id":"1812.00891","title":"Interpretable Deep Learning under Fire","created":"2018-12-03","cited_by_count":74},{"id":"2405.12241","title":"Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning","created":"2024-05-17","cited_by_count":67},{"id":"1906.11583","title":"Approximate Causal Abstraction","created":"2019-06-27","cited_by_count":63},{"id":"2407.10827","title":"LLM Circuit Analyses Are Consistent Across Training and Scale","created":"2024-07-15","cited_by_count":63},{"id":"1802.04223","title":"SparseMAP: Differentiable Sparse Structured Inference","created":"2018-02-12","cited_by_count":62},{"id":"2004.08500","title":"A Formal Hierarchy of RNN Architectures","created":"2020-04-18","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":"1707.01943","title":"A causal framework for explaining the predictions of black-box sequence-to-sequence models","created":"2017-07-06","cited_by_count":58},{"id":"1801.07772","title":"Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks","created":"2018-01-23","cited_by_count":56},{"id":"1711.08792","title":"SPINE: SParse Interpretable Neural Embeddings","created":"2017-11-23","cited_by_count":55},{"id":"2010.02180","title":"Pareto Probing: Trading Off Accuracy for Complexity","created":"2020-10-05","cited_by_count":55},{"id":"1611.07270","title":"Investigating the influence of noise and distractors on the interpretation of neural networks","created":"2016-11-22","cited_by_count":54},{"id":"2005.01172","title":"Similarity Analysis of Contextual Word Representation Models","created":"2020-05-03","cited_by_count":54},{"id":"2305.18741","title":"Grokking of Hierarchical Structure in Vanilla Transformers","created":"2023-05-30","cited_by_count":53},{"id":"1711.07414","title":"The Promise and Peril of Human Evaluation for Model Interpretability","created":"2017-11-20","cited_by_count":52},{"id":"2408.00113","title":"Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models","created":"2024-07-31","cited_by_count":51},{"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":"2402.12560","title":"CausalGym: Benchmarking causal interpretability methods on linguistic tasks","created":"2024-02-19","cited_by_count":46},{"id":"2105.07109","title":"The Low-Dimensional Linear Geometry of Contextualized Word Representations","created":"2021-05-15","cited_by_count":40},{"id":"1602.08952","title":"Representation of linguistic form and function in recurrent neural networks","created":"2016-02-29","cited_by_count":39},{"id":"1606.07298","title":"Explaining Predictions of Non-Linear Classifiers in NLP","created":"2016-06-23","cited_by_count":37},{"id":"1901.11184","title":"Human-Centered Artificial Intelligence and Machine Learning","created":"2019-01-31","cited_by_count":37},{"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":"2112.06837","title":"Sparse Interventions in Language Models with Differentiable Masking","created":"2021-12-13","cited_by_count":34},{"id":"1901.10444","title":"No Training Required: Exploring Random Encoders for Sentence Classification","created":"2019-01-29","cited_by_count":32},{"id":"2105.10185","title":"A Non-Linear Structural Probe","created":"2021-05-21","cited_by_count":31}],"next_cursor":"100"}