SAE Loss

normalized version of all MSE numbers, where we divide by a baseline reconstruction error of always predicting the mean activations

Auxiliary-K loss

SAE Feature Direction Loss

Reconstruction dark matter within
Dictionary Learning

A significant portion of SAE reconstruction error can be linearly predicted, but there exists a nonlinear error that does not decrease even when increasing the size. Therefore, additional techniques are needed to reduce nonlinear error.

arxiv.org

https://arxiv.org/pdf/2410.14670

Circuits Updates - July 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.

https://transformer-circuits.pub/2024/july-update/index.html#dark-matter

While end-to-end training with KL divergence requires more computational resources, using KL divergence just for fine-tuning proves to be effective.

arxiv.org

https://arxiv.org/pdf/2503.17272

SAE Loss

Reconstruction dark matter within Dictionary Learning

Recommendations

Reconstruction dark matter within
Dictionary Learning