thinker:demian-tillDemian Till
Authored papers (1)
Gains on the sparsity-fidelity frontier do not predict how well a sparse autoencoder performs on downstream tasks, and SAEBench demonstrates this by scoring over 200 SAEs on eight metrics. Matryoshka BatchTopK SAEs rank below TopK and BatchTopK on loss recovered, yet they take the best score on Absorption, RAVEL, Sparse Probing, SCR and TPP, which is 5 of 8 metrics, in the typical L0 range of 40-200. Matryoshka is also the only architecture whose disentanglement scores improve when width grows from 4k to 16k to 65k latents on Gemma-2-2B (layer 12). The other architectures show inverse scaling on absorption and SCR, and the effect persists when the number of ablated latents is held fixed. SAEBench combines four capability groups (concept detection, interpretability, reconstruction, feature disentanglement). It adds two novel zero-ablation metrics, Spurious Correlation Removal and Targeted Probe Perturbation, and it extends the absorption metric to partial and shared absorption. The suite covers seven architectures (ReLU, TopK, BatchTopK, Gated, JumpReLU, P-annealing, Matryoshka), Gemma-2-2B and Pythia-160M, and Gemma-Scope SAEs up to 1M latents. Hierarchical architectures beat the rest by 30-40% on SCR and absorption. No single L0 wins everywhere, though L0 of 50-150 is a reasonable compromise. The implication is that SAE progress needs a multi-metric benchmark, and that optimizing reconstruction at fixed sparsity can hide failures in concept isolation, which grow with scale. The paper declines to combine the metrics into one score.
More papers — OpenAlex / S2
Co-authors (12)
- Adam Karvonen9 shared
- Arthur Conmy9 shared
- Can Rager9 shared
- Curt Tigges9 shared
- Johnny Lin9 shared
- Joseph Bloom9 shared
- Kola Ayonrinde9 shared
- Matthew Wearden9 shared
- Neel Nanda9 shared
- Callum Stuart McDougall6 shared
- Chanin, David6 shared
- Farrell, Eoin6 shared
Other inbound relations (1)
Recent mentions (1)
- papers-typedkarvonen-2025-saebench-comprehensive.md