position-embeddings-encode-digit-place-let-small-transformersmechanismsingle paper
Position embeddings that encode digit place let small transformers add 100-digit numbers, showing the limit is representational not fundamental.
Capability: Digit-level arithmetic
Sources
- Position embeddings that encode digit place let small transformers add 100-digit numbers, showing the limit is representational not fundamental.
Disagreeing is the most useful thing you can do here. Both sides of every contested claim in this catalog were assembled by the same person, which is its weakest point.