concept
active
concept:overcomplete-basisOvercomplete Basis
A set of feature directions that is larger than the dimensionality of the space, enabling superposition
Neighborhood — ranked by edge-count
Frameworks (1)
framework
- Superposition Hypothesisassociated_withCore theoretical framework: neural networks represent more features than neurons by encoding features as directions in superposition
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- TUAI failure mode: generating normative predictions faster than they can be fulfilled.
- A strategic error where a bid exceeds the bidder's available money, triggering wealth revelation and auction restart.
- fraction of auctions in which an agent submitted a bid exceeding its total money, triggering wealth revelation penalty
- Attribute: placing one text on top of another, partially obscuring, as an act of layering.
- Parameters of the approximate posterior, such as Dirichlet counts for model parameters.
- A property of activations where neural network features align with basis dimensions due to sparse activation functions; absent in the residual stream but present in tokens, attention patterns, and MLP activations
- Fraction of auctions where the agent bids more than its total money, triggering wealth revelation.