paper
referenced-only
paper:dark-matter-c53b64The dark matter of neural networks? Transformer Circuits Thread
Similar preprints — Semantic Scholar
Cited by (1)
- Understanding sparse autoencoder scaling in the presence of feature manifolds
Sparse autoencoder scaling laws can break down when activations contain feature manifolds: if per-feature loss falls slowly with latent count, an SAE spends its latents tiling common manifolds instead