Gated SAE

Creator

Creator

Seonglae Cho

Created

Created

2024 Oct 24 0:13

Editor

Editor

Seonglae Cho

Edited

Edited

2025 Mar 28 12:0

Refs

Refs

Gated SAE

While L1 loss enforces sparsity, it can excessively reduce important features through shrinkage, making it difficult to properly represent the data.

L1 penalty is only applied during the process of selecting (gating) which features to activate

The degree of activation for selected neurons is determined without L1 penalty

In other words, feature activation remains sparse while preventing the L1 penalty from reducing the actual magnitude of values

Gated SAEs

https://www.lesswrong.com/posts/EWhA4pyfrbdSkCd4G/evaluating-sparse-autoencoders-with-board-game-models

JumpReLU SAE with
Unit step function

Does this mean they efficiently implemented the gating mechanism using JumpReLU activation?

notion image

notion image

anthropic analysis

Circuits Updates - June 2024

We report a number of developing ideas on the Anthropic interpretability team, which might be of interest to researchers working actively in this space. Some of these are emerging strands of research where we expect to publish more on in the coming months. Others are minor points we wish to share, since we're unlikely to ever write a paper about them.

Circuits Updates - June 2024

https://transformer-circuits.pub/2024/june-update/index.html#topk-gated-comparison

Gated SAE

https://arxiv.org/pdf/2404.16014

openai comparison against topk

https://arxiv.org/pdf/2406.04093

Recommendations

///////////