{"categories":[{"label":"Scientific/Engineering","url":"https://skillfed.io/packages/category/scientific-engineering/4"}],"enrichment":{"capability":"Captum provides model interpretability algorithms for PyTorch, including integrated gradients, saliency maps, and other attribution methods to understand which features and training examples drive model predictions.","skillfed_tags":["model-explainability","pytorch-ecosystem","interpretability"],"use_cases":["Debug unexpected model predictions by identifying which input features most influenced the output.","Validate that a model learned meaningful patterns rather than spurious correlations in training data.","Generate explanations for end users on why a model made a specific recommendation or classification decision.","Benchmark new interpretability algorithms against established methods in the Captum library.","Identify important neurons and layers within a network to guide model compression or architecture redesign."],"what_it_does":"Captum is a PyTorch library for understanding and interpreting neural network predictions by computing attribution scores that show which input features, neurons, or training examples contribute most to a model's output. It implements state-of-the-art interpretability algorithms including Integrated Gradients, DeepLift, TCAV, and TracIn influence functions, along with adversarial perturbation capabilities for generating counterfactual explanations.\n\nThe library is designed for model developers who need to debug and improve their models, interpretability researchers benchmarking new algorithms, and production engineers troubleshooting model behavior. It integrates with domain-specific PyTorch libraries like torchvision and torchtext, and provides convergence metrics to assess approximation quality for gradient-based attribution methods.","worth_installing":"Yes. Captum is a production-stable, actively maintained library from PyTorch with no known vulnerabilities, low install friction, and permissive licensing. It is the standard choice for PyTorch model interpretability and is worth installing if you need to understand or explain neural network predictions."},"id":"captum","links":{"html":"https://skillfed.io/packages/captum","md":"https://skillfed.io/packages/captum.md","pypi":"https://pypi.org/project/captum/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-04-17","license_spdx":"BSD-3-Clause","license_treatment":"permissive","name":"captum","python_support":"supports_current","summary":"Model Interpretability for PyTorch"},"popularity":{"monthly_downloads":548326,"position":6064,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"0.9.0"}