"You saw it work; now open it up." Visual tools that let you watch what a neural network learns and how it decides — by clicking, not by reading formulas.
Almost no math here. Changing a value and watching the result shift sticks far better than an equation.
Start with separating a few dots. Feel what changes as neurons and layers pile up.
A hands-on page where you train a small neural network right in the browser. Change the number of layers and neurons, the activation function, or the learning rate, and watch how the decision boundary shifts. There is no model to download, so it runs the moment you open it.
ConvNetJS is a library that allows you to train deep learning models in the browser. Through the demo, you can visualize the learning process and results of the neural network.
A tool for following, step by step, how word2vec builds its word vectors. Feed it a tiny training set such as 'eat|apple, drink|milk' and run training: the cells of the input and output weight matrices shift colour a little at a time while the word points settle into place in the PCA plot below. You come away understanding that an embedding is not a value fixed in advance but something produced gradually by repeated training.
A TensorFlow tool that reduces embeddings — data such as words represented as vectors of hundreds of dimensions — down to two or three dimensions you can look at. It opens on 10,000 Word2Vec words in 200 dimensions, and picking one word lists its nearest neighbours. You come away seeing directly that words with related meanings sit close together in the space.
Watch one picture transform layer by layer, and see what each filter latches onto.
This is a program implemented to help users easily understand the inner workings of CNN. You can visualize the image recognition process step by step.
A visualization that unfolds the inside of a convolutional neural network (CNN) recognizing handwritten digits into three dimensions. You can watch a drawing get summarized into smaller, more abstract values as it passes from the input layer through convolution, downsampling, fully-connected and output layers. It helps you understand that a neural network is not one opaque box but a chain of layers with different jobs.
Load deep learning models pre-trained with TensorFlow and output them as 3D visualization scenes. You can visualize the processing of each model.
Follow it step by step: text splits into tokens, words attend to each other, and the next word gets picked.
A page that colors in how your sentence is split into tokens inside an AI model. You can pick and compare the tokenizers of 13 models including GPT-4, Claude, Llama 3, Gemma, Mistral, BERT, and T5.
A tool for seeing how a language model splits text into tokens. Type something and it immediately shows the token count, the colour-coded token pieces and the numeric ID of each token. You can also see the special markers that wrap a conversation before it reaches the model.
A teaching visualization that walks step by step through how a GPT-style language model picks the next word. It actually runs GPT-2 (small) in the browser so you can follow your sentence turning into tokens and embeddings, passing through self-attention and an MLP, and ending as next-word probabilities. You come away understanding that a language model is not magic but a machine computing which word is most likely to come next.
An interactive tool that lays out a transformer model's attention patterns by layer and head so they can be compared side by side. Because query and key vectors are projected into the same space, you can see at a glance that different heads produce quite different shapes. You come away seeing that attention heads each track different relationships — note that it assumes you already know how transformers are structured.
A guided tour that unfolds the inside of a GPT language model in 3D and walks you from top to bottom. It starts with nano-gpt, a model of just 85,000 parameters, doing one simple task: sorting a string like "C B A B B C" into alphabetical order. You come away with a feel for what actually happens at each layer as numbers become embeddings, pass through the stack, and end as next-token probabilities.
GANs that compete, and diffusion that lifts an image out of noise — the two pillars of generative AI.
This is a program that allows you to examine the learning process of GAN in real time with an interactive visualization tool. The operation process of the generator and discriminator for 2D data is presented as an example.
A visualization that walks step by step through how Stable Diffusion turns text into an image. On one screen you can follow how the prompt is split into tokens, encoded into vectors, refined from random noise over many timesteps, and finally upscaled.
