wevi (Word Embedding Visual Inspector)
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.
How to try it
Choose an example such as 'Fruit and juice (CBOW)' or 'King and queen' under Presets, press 'Update and Restart', then advance training as far as you like with 'Next' or the 20 / 100 / 500 buttons. The Neurons, Weight Matrices, Vectors and PCA views show the same training from different angles, and you can edit the training data, hidden size and learning rate yourself. The interface is English only and the layout is wide, so a desktop browser is recommended.