Search Packages

glassbox-mech-interp

Mechanistic interpretability + EU AI Act Annex IV compliance. 21/21 frameworks: ACDC edge-circuit discovery, multi-arch GQA/RMSNorm adapter (Llama-3/Mistral/Phi-3), cross-model comparison, causal scrubbing, DAS, Hessian bounds, BH FDR, folded LayerNorm, SAE polysemanticity, multi-corruption, held-out validation. Dual-licensed (MIT core + BSL 1.1 compliance engine).

reptimeline

Track how discrete representations evolve during neural network training — lifecycle events, phase transitions, ontology discovery, and causal verification

tiny-dashboard

A tool for visualizing and exploring feature activations in neural language models.

hypothesaes

HypotheSAEs: hypothesizing interpretable relationships in text datasets using sparse autoencoders. https://arxiv.org/abs/2502.04382

glassbox-mcp

Open-source EU AI Act Annex IV compliance toolkit. Mechanistic interpretability + circuit discovery for transformers. One function call generates a court-ready evidence package