litlas
Log inCreate account

Zoom In: An Introduction to Circuits

Authors: Chris Olah, Nick Cammarata, Ludwig Schubert, Gabriel Goh, Michael Petrov, Shan Carter - Distill 2020 cited by 257

ImageNet Classificationwith Deep Convolutional…ImageNet Classification with Deep Convolutional Neural NetworksGoing Deeper withConvolutionsGoing Deeper with ConvolutionsDeep learningDeep learningDeep Residual Learningfor Image RecognitionDeep Residual Learning for Image RecognitionMultifaceted FeatureVisualization…Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural NetworksFeature VisualizationFeature VisualizationNetwork Dissection:Quantifying…Network Dissection: Quantifying Interpretability of Deep Visual RepresentationsThe Building Blocks ofInterpretabilityThe Building Blocks of InterpretabilityOn the importance ofsingle directions for…On the importance of single directions for generalizationActivation AtlasActivation AtlasSimilarity of NeuralNetwork Representations…Similarity of Neural Network Representations RevisitedSummit: Scaling DeepLearning…Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution SummarizationsTowards falsifiableinterpretability…Towards falsifiable interpretability researchInvestigating Learningin Deep Neural Networks…Investigating Learning in Deep Neural Networks Using Layer-Wise Weight ChangeExemplary Natural ImagesExplain CNN Activations…Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature VisualizationVisualizing WeightsVisualizing WeightsAdversarialPerturbations Are Not S…Adversarial Perturbations Are Not So Weird: Entanglement of Robust and Non-Robust Features in Neural Network ClassifiersDo Invariances in DeepNeural Networks Align…Do Invariances in Deep Neural Networks Align with Human Perception?Deeply Explain CNN ViaHierarchical…Deeply Explain CNN Via Hierarchical DecompositionMethods for identifyingemergent concepts in…Methods for identifying emergent concepts in deep neural networksToward Transparent AI: ASurvey on Interpreting…Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural NetworksA MechanisticInterpretation of…A Mechanistic Interpretation of Arithmetic Reasoning in Language Models using Causal Mediation AnalysisExplaining AI throughmechanistic…Explaining AI through mechanistic interpretabilityArtificial Neural Netsand the Representation…Artificial Neural Nets and the Representation of Human ConceptsZoom In: An Introductionto CircuitsZoom In: An Introduction to CircuitsEarlier referencesFocus paperCiting papersOlderNewer

Click a node to pin it, click the empty canvas to go back to this paper, or hover to preview. Open a node’s page from its title.