Downloads · 30 days
0
decoderesearch/synth-sae-bench-16k-v1-saes
synth-sae-bench-16k-v1-saes is a machine learning model from decoderesearch. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for saelens. The card lists the license as mit.
Sample Sparse Autoencoders (SAEs) trained on the SynthSAEBench-16k-v1 model. Training code is at https://github.com/decoderesearch/synth-sae-bench-experiments.
Downloads · 30 days
0
Access
Public
Updated May 28, 2026
Repo size
6.6 GB
Likes
0
Public
Click a slice to open those files.
.safetensors4 GB · 100%
From the Hugging Face model README
Sample Sparse Autoencoders (SAEs) trained on the SynthSAEBench-16k-v1 model. Training code is at https://github.com/decoderesearch/synth-sae-bench-experiments.
We train 5 different SAE types, each with 5 seeds and L0 from 15-45. Each SAE has a stats.json file containing eval stats.
Check out SAELens to train your own SAEs on SynthSAEBench and make your own custom synthetic data models. Also see the SynthSAEBench paper for more details.