Domain Neighborhood
Representation Learning
Embeddings and the geometry of meaning: similarity, normalization, contrastive objectives, and why vector spaces become usable interfaces for models.
Recommended Route
Start here, then follow the prerequisites forward.
This sequence is ordered for learning rather than inventory: lower difficulty, fewer prerequisites, and more central concepts come first.
- 01Representation 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 LayersCheck Scaled Dot-Product Attention & Transformer Layers first if the symbols feel slippery.
- 02Autoencoders and Denoising Autoencoders
Autoencoders learn codes by reconstructing inputs; denoising autoencoders reconstruct clean targets from corrupted inputs, so the useful lesson is compression plus constraint, not magic understanding.
18 mincodedemoafter PCA as Optimization and Eigenspace Projection, Gradient Descent, BackpropagationWhy this follows: both pages keep the representation learning thread active.
- 03Sparse 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, probingWhy this follows: both pages keep the representation learning / autoencoders thread active.
All Published Notebooks
Browse the territory.
Representation Learning & Embedding Geometry
How models turn inputs into vectors whose geometry can expose useful factors, contextual meaning, and similarity structure.
Autoencoders and Denoising Autoencoders
Autoencoders learn codes by reconstructing inputs; denoising autoencoders reconstruct clean targets from corrupted inputs, so the useful lesson is compression plus constraint, not magic understanding.
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.
Advanced Bridges