── POPULAR TAGS ──
#python (662)
#typescript (613)
#cli (563)
#hacktoberfest (492)
#cli-tool (485)
#react (481)
#javascript (449)
#rust (418)
#cross-platform (388)
#go (372)
#devops (317)
#ai (304)
#llm (298)
#nodejs (298)
#golang (287)
#android (271)
#open-source (255)
#docker (249)
#machine-learning (220)
#java (217)
#security (214)
#monorepo (214)
#plugin-system (214)
#self-hosted (211)
#linux (207)
#mcp (203)
#awesome-list (197)
#plugin-architecture (195)
#deep-learning (187)
#ai-agents (187)
bertviz is a Python library for interactive visualization of attention in Transformer-based NLP models. It provides three complementary views: Head View (per-head attention patterns), Model View (attention flow between tokens across layers), and Neuron View (query/key interactions within individual attention heads). The library is designed for Jupyter notebooks, rendering D3.js-based interactive HTML directly in cell output. It accepts attention tensors from most HuggingFace models via output_attentions=True, and includes a vendored, modified copy of older HuggingFace transformers code to expose query/key vectors for the Neuron View on BERT, GPT-2, RoBERTa, XLNet, and similar architectures.
RATING:
MAINT: maintained
DRIFT: high
▸ 3 reusable components found
── end of results ──