Tag: language model interpretability
Browse our exclusive articles!
E-TCAV: Efficient Concept-Based Neural Network Interpretability
Discover E-TCAV, a faster and more reliable method enhancing TCAV for real-time concept-based neural network interpretability and model debugging.
Data-driven Circuit Discovery for Interpreting Language Models
Discover how Data-driven Circuit Discovery (DCD) enhances interpretability of language models by revealing multiple task-specific circuits.
Detecting Backdoors in SAE Architectures: Diff-SAE vs Crosscoders
Explore how Diff-SAE outperforms Crosscoders in isolating backdoors in language models, enhancing AI safety through effective detection methods.
Generalized Singular Value Theory for Neural Networks
Discover how Generalized Singular Value Decomposition enhances neural network analysis, robustness, and adversarial defense in modern AI models.
Temporal Functional Circuits for Accurate KAN Forecasting
Discover how Temporal Functional Circuits improve KAN forecasting with interpretable spline plots and enhanced prediction accuracy in time-series models.