Transformer Explainer (How a Transformer Works)
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.
How to try it
Type an English sentence in the box at the top or pick one from "Examples," then press "Generate" to fill the stages with real values. Change Temperature, Top-k, and Top-p to compare how the next-word probability list shifts, and hover over the embedding rectangles or the attention section for detailed explanations. The interface is English only, and the first run takes time while the 600MB GPT-2 model downloads.