Embeddings & Representations

The lookup table, the residual stream, contextual vectors, geometry and superposition.

17concepts
177flashcards
126minutes of reading
  1. 01 Cross-Lingual Embedding Alignment Putting a hundred languages into one vector space so that a Hindi query retrieves an English document requires an explicit alignment signal, and the way you supply it determines exactly how the space fails. advanced 8m 24 cards
  2. 02 Embedding Geometry and Anisotropy Learned embedding spaces are not the well-spread sphere the geometric intuition suggests, they collapse into a narrow cone, and that fact quietly breaks naive similarity comparisons built on top of them. advanced 8m 4 cards
  3. 03 Hard Negative Mining and Contrastive Embedding Training A retrieval embedder is only as good as the negatives it was trained against, and the gap between easy in-batch negatives and mined hard negatives is the single largest lever in dual-encoder training. advanced 8m 24 cards
  4. 04 Hubness in High-Dimensional Retrieval In high-dimensional spaces a small number of points appear in almost everyone's nearest-neighbour list regardless of relevance, which is a property of the geometry rather than a bug in the embedder. advanced 7m 24 cards
  5. 05 Superposition and Polysemantic Neurons Individual neurons in a trained network routinely fire for several unrelated concepts at once, and the leading explanation is not noise, it is a model deliberately packing more features than it has dimensions using near-orthogonal directions. advanced 9m 5 cards
  6. 06 The Residual Stream Reframing a transformer's residual connections as one shared, additive vector space that every layer reads from and writes to, the lens that makes attention, MLPs, and interpretability results legible as a single system. advanced 9m 4 cards
  7. 07 Unembedding and the Logit Lens Multiplying an intermediate layer's residual stream by the final unembedding matrix, as if it were the last layer, turns out to produce surprisingly sensible next-token guesses, a cheap window into what a model has committed to mid-computation. advanced 8m 5 cards