metadata
license: mit
library_name: pytorch
tags:
- coconut
- latent-chain-of-thought
- sparse-autoencoder
- qwen3
SAE on Coconut latent thoughts (Qwen3-1.7B)
SAE bottleneck trained on the frozen Stage-3 Coconut latent thoughts of Qwen3-1.7B, from the VQ-CoT: Discretising Latent Chain-of-Thought project (team RateLimit Achieved, EPFL CS-552). The language model is frozen; only this bottleneck is trained on the dumped latents (385,620 x 6 latent thought vectors, GSM8K).
- Checkpoint:
sae.pt - TopK SAE, dictionary 8x hidden, k=32 active features
- Result: inserting this bottleneck into the frozen latent loop costs ~0 GSM8K test accuracy.