If training Gated SAEs [1] with Anthropic's new training techniques [2] gives equal loss recovered with <90% of the L0 value of either of the techniques individually applied, at the majority of sites in Pythia-2.8B / Gemma-7B / Mistral-7B (whichever actually gets benchmarked), this resolves yes.

Resolves when information is publicly available about the outcome.

I haven't implemented [2] yet so have no insider information, and also I will not trade in this market besides an initial bet.

[1]: https://arxiv.org/abs/2404.16014

[2]: https://transformer-circuits.pub/2024/april-update/index.html#training-saes

RESOLUTION:

https://arxiv.org/pdf/2407.14435 shows by loss recovered there is minimal benefit (mostly cos Anthropics update primarily address lower dead features, not better perf)