Domain Neighborhood

Representation Learning

Embeddings and the geometry of meaning: similarity, normalization, contrastive objectives, and why vector spaces become usable interfaces for models.

3 concepts2 published3 demos

Recommended Route

This sequence is ordered for learning rather than inventory: lower difficulty, fewer prerequisites, and more central concepts come first.

  1. 01
    Representation Learning & Embedding Geometry

    How models turn inputs into vectors whose geometry can expose useful factors, contextual meaning, and similarity structure.

    18 mincodedemoafter Scaled Dot-Product Attention & Transformer Layers

    Check Scaled Dot-Product Attention & Transformer Layers first if the symbols feel slippery.

  2. 02
    Sparse Autoencoders: Feature Dictionaries for Mechanistic Interpretability

    Sparse autoencoders learn a reusable dictionary of feature directions so dense model activations can be explained by a small set of interpretable latent factors.

    16 mincodedemoafter Representation Learning & Embedding Geometry, superposition, probing

    Why this follows: Sparse Autoencoders: Feature Dictionaries for Mechanistic Interpretability uses Representation Learning & Embedding Geometry directly.

All Published Notebooks

Browse the territory.

Advanced Bridges

Use these after the core path.

In Progress

Notebooks still below the publish bar.

Autoencoders and Denoising Autoencoders