Interactive Tools

A real-time Python code execution environment powered by WebAssembly.

Advanced code editing environment with rich features.

Interactive data visualization tool for creating graphs and charts.

Dynamic visualization tool for understanding memory allocation and management.

Interactive tool for visualizing variable states and data types.

Visual representation tool for control flow and program execution.

Visualizes different text tokenization approaches with interactive controls.

Interactive comparison table for visualizing differences between related techniques.

Interactive visualization of the Byte-Pair Encoding algorithm steps.

Compare different tokenization approaches used in modern NLP models.

Visualize how words appear in similar contexts, illustrating the distributional hypothesis.

Interactive visualization of CBOW and Skip-gram architectures in Word2Vec.

Interactive 2D visualization of word embeddings, allowing exploration of relationships between words.

Interactive 2D visualization of word embeddings, allowing exploration of relationships between words.

Compare performance and characteristics of different word embedding models like Word2Vec, FastText, and GloVe.

Compare performance and characteristics of different word embedding models like Word2Vec, FastText, and GloVe.

Explore how contextual embeddings help disambiguate words with multiple meanings in different contexts.

Explore how contextual embeddings help disambiguate words with multiple meanings in different contexts.

A unified visualization tool for exploring word vectors, analogies, model comparisons, contextual relationships, and attention mechanisms.

2D visualization of word vectors and their relationships.

Visualize word analogies in vector space (e.g., king - man + woman = queen).

Compare performance and characteristics of different word embedding models like Word2Vec, FastText, and GloVe.

Explore how words shift their positions in embedding space depending on context.

Visualize how attention mechanisms connect words in sequences.

Interactive visualization of different RNN architectures including vanilla RNN, LSTM, GRU, and bidirectional variants.

Visualize the process of Backpropagation Through Time (BPTT) and understand the vanishing gradient problem in RNNs.

Visualize how different RNN architectures attend to words in a sequence, with support for coreference highlighting.

Compare processing time between different model architectures at various sequence lengths.

Visualize how effectively different models can use context at various distances.

Visualize the encoder-decoder architecture used in sequence-to-sequence tasks.

Compare translation quality between statistical, RNN, and transformer-based models.

Visualize and analyze how bidirectional models understand context through multiple word senses

Compare Vanilla RNN, LSTM, and GRU architectures side by side

Visualize attention weights in a machine translation scenario.

Interactive visualization of the transformer architecture with encoder and decoder components.

Step-by-step visualization of the self-attention calculation process.

Visualization of how multiple attention heads work together in transformer models.

Visualization of sinusoidal positional encodings used in transformer models.

Visualization of the transformer encoder architecture with self-attention and feed-forward networks.

Visualization of causal and padding masks used in transformer decoder models.

Visualization of the transformer decoder with masked self-attention and cross-attention.

Visualization of cross-attention between encoder and decoder in transformer models.

Visualization of how word embeddings and positional encodings are combined.

Comparison of different transformer-based model architectures.

An interactive tool for cleaning and normalizing text with configurable options.

Comprehensive tool for exploring the full text preprocessing pipeline.

Interactive demonstration of SentencePiece tokenization.

Interactive demonstration of word analogies in embeddings space.