Glossary · Term

subspace

← all terms

Definition

Plain language

A slice of the model's internal number space — some of its directions, not all of them.

As stated in the literature

A linear subset of a representation space; projection-based edits act only within a chosen subspace, leaving information encoded in orthogonal directions untouched, which is why learning can route around a simulated ablation.

Also called: subspaces

Why it matters: It explains why removing one direction is not the same as removing a capability — the information can simply be re-encoded in a direction the edit never touched.

For example, an edit that removes one internal direction is like erasing a single line of an address while the rest of it stays perfectly readable.

Heard on the show

“And it's a subtraction inside one specific subspace, which means anything represented in the directions it doesn't touch comes through untouched.”
Episode 244 — The Open-Weight Defense That Feeds Attackers Confident, Falsified Answers

Mentioned in 8 episodes

  1. 244
    The Open-Weight Defense That Feeds Attackers Confident, Falsified Answers
  2. 193
    Freeze Most of the Network: Where RL Improvement Actually Lives in a Transformer
  3. 175
    One Crosscoder Feature Flips a Stalling Chatbot Into a Working Agent
  4. 118
    Why the Best-Aligned AI Models Are the Easiest to Trick Into Producing Harm
  5. 055
    Why LLM Judges Flip Their Verdicts When You Change the Question Format
  6. 038
    How LLMs Get Persuaded: One Attention Head, A Tetrahedron, And A Single Dial
  7. 037
    Why Hallucination Detectors Miss Stale Facts: A Geometric Story About What Models Know But Don't Say
  8. 036
    Sparse Attention Was the Wrong Frame. Treat It as Geometry Instead.

Related concepts

Related terms