conftrace_

concept activation

8 papers

Explore in graph

Co-occurring keywords · papers mentioning both

neural network (2) feature attribution (2) jensen-shannon distance (1) monosemantic representation (1) gender bias correction (1) feature factorization (1) kernel methods (1) text generation control (1) lidar-based detection (1) neural network explanation (1)

Papers

Beyond Patches: Mining Interpretable Part-Prototypes for Explainable AI AAAI 2026 Evaluating Sparse Autoencoders for Monosemantic Representation EACL 2026 Interpretable Failure Detection with Human-Level Concepts AAAI 2025 FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors NeurIPS 2024 Concept Activation Regions: A Generalized Framework For Concept-Based Explanations NeurIPS 2022 Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation ICLR 2022 Self-conditioning Pre-Trained Language Models ICML 2022 Neural Vector Conceptualization for Word Vector Space Interpretation NAACL 2019