PAIR code ORG

Visualizations for machine learning datasets

Two browser-based tools that let you visually explore machine learning datasets, one shows statistics per data column to catch quality issues, the other lets you zoom into individual data points across tens of thousands of items.

The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.

Source code/webpage/demos for the What-If Tool

Framework-agnostic implementation for state-of-the-art saliency methods (XRAI, BlurIG, SmoothGrad, and more).

LLM Comparator is an interactive data visualization tool for evaluating and analyzing LLM responses side-by-side, developed by the PAIR team.

JavaScript implementation of UMAP

✨✍️ Wordcraft is an AI-powered text editor with an emphasis on short story writing

A tool to help researchers and product teams understand datasets with the goal of improving data quality, and mitigating fairness and bias issues.

PAIR.withgoogle.com and friend's work on interpretability methods

The Data Cards Playbook helps dataset producers and publishers adopt a people-centered approach to transparency in dataset documentation.

Lumi uses AI-powered features to help you read arXiv papers.

Understanding the theory behind UMAP

Interactive 3D / 2D webgl-accelerated scatter plot point renderer

Federated learning experiment using TensorFlow.js

Platform for running online research experiments on human + LLM group dynamics.

https://pair.withgoogle.com/explorables/

𝄡 Collaborative Convolutional Counterpoint

AutoNotes is an experimental prototype for AI-powered notetaking, with features including hierarchical tagging, "chat with your notes," and highlights.

Model Alignment is a python library from the PAIR team that enable users to create model prompts through user feedback instead of manual prompt writing and editing. The technique makes use of constitutional principles to align prompts to users' desired values.

Font latent space explorer using tensorflow.js

Cam Scroller is an open-source Chrome extension that uses your webcam and deeplearn.js to enable scrolling through webpages using custom gestures that you define.

No description.

A javascript medical record visualization (https://arxiv.org/abs/1810.05798)

In situ interactive widgets for responsible AI 🌱

No description.

No description.

No description.

No description.

Supplementary code repository to accompany Tic-Tac-Toe the Hard Way podcast

No description.

No description.

No description.

No description.

No description.

Visualizing multilevel structure in books with sentence embeddings.

No description.

No description.

Deprecated: Legacy TensorFlow model loader for deeplearn.js

An interactive visualization interface for exploring and analyzing the Adversarial Nibbler dataset

No description.

No description.

No description.

No description.

No description.