neural network interpretability

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 EMNLP 2024 HANS, are you clever? Clever Hans Effect Analysis of Neural Systems NAACL 2024 Interpreting Context Look-ups in Transformers: Investigating Attention-MLP Interactions EMNLP 2024 Interpreting Learned Feedback Patterns in Large Language Models NeurIPS 2024 Measuring Per-Unit Interpretability at Scale Without Humans NeurIPS 2024 Pathwise Explanation of ReLU Neural Networks AISTATS 2024 Pixel-Grounded Prototypical Part Networks WACV 2024 Structured Gradient-based Interpretations via Norm-Regularized Adversarial Training CVPR 2024 Token Erasure as a Footprint of Implicit Vocabulary Items in LLMs EMNLP 2024 Towards Modeling Uncertainties of Self-Explaining Neural Networks via Conformal Prediction AAAI 2024 Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis EMNLP 2024 Brain Dissection: fMRI-trained Networks Reveal Spatial Selectivity in the Processing of Natural Images NeurIPS 2023 Cardinality-Minimal Explanations for Monotonic Neural Networks IJCAI 2023 Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement NeurIPS 2023 Cones: Concept Neurons in Diffusion Models for Customized Generation ICML 2023 CRAFT: Concept Recursive Activation FacTorization for Explainability CVPR 2023 Defining and Quantifying the Emergence of Sparse Concepts in DNNs CVPR 2023 Disentangling Transformer Language Models as Superposed Topic Models EMNLP 2023 Easy to Decide, Hard to Agree: Reducing Disagreements Between Saliency Methods ACL 2023 Experimental Observations of the Topology of Convolutional Neural Network Activations AAAI 2023 Formal Explanations of Neural Network Policies for Planning IJCAI 2023 Gaussian Process Surrogate Models for Neural Networks UAI 2023 Latent Inspector: An Interactive Tool for Probing Neural Network Behaviors Through Arbitrary Latent Activation IJCAI 2023 MoreauGrad: Sparse and Robust Interpretation of Neural Networks via Moreau Envelope ICCV 2023 Negative Flux Aggregation to Estimate Feature Attributions IJCAI 2023