Visualization for Machine Learning (Google Brain)

https://github.com/microsoft/data-formulator?tab=readme-ov-file

https://pair-code.github.io/facets/

https://pair-code.github.io/what-if-tool/

https://projector.tensorflow.org/

https://github.com/HendrikStrobelt/Seq2Seq-Vis?tab=readme-ov-file

https://poloclub.github.io/ganlab/

https://distill.pub/

https://playground.tensorflow.org/#activation=tanh&batchSize=10&dataset=circle&regDataset=reg-plane&learningRate=0.03&regularizationRate=0&noise=0&networkShape=4,2&seed=0.19904&showTestData=false&discretize=false&percTrainData=50&x=true&y=true&xTimesY=false&xSquared=false&ySquared=false&cosX=false&sinX=false&cosY=false&sinY=false&collectStats=false&problem=classification&initZero=false&hideText=false

https://quickdraw.withgoogle.com/data

https://yosinski.com/deepvis

http://www.r2d3.us/visual-intro-to-machine-learning-part-1/ TensorBoard

Bertviz

BertViz is the most widely-used open-source tool for attention visualization. It supports multiple transformer models and provides three distinct views

https://github.com/jessevig/bertviz

Inspectus

Inspectus is a newer, versatile visualization library specifically designed for LLMs. It offers:

• Attention Matrix: Interactive heatmaps showing token-to-token attention scores
• Query/Key Token Heatmaps: Specialized views for understanding attention flow
• Dimension Heatmaps: Attention scores across layers and heads
• Simple Python API: Easy integration with Jupyter notebooks

SAVIS: Sentence-Level Attention Visualization for Large Language Models

SAVIS (Sentence-level Attention VISualization) is a Python library for visualizing inter-sentence attention in large language models (LLMs). This tool enhances the interpretability of LLMs by providing an intuitive visualization of how attention is distributed across sentences in generated text.

https://github.com/shap/shap A game theoretic approach to explain the output of any machine learning model.