Downloads · 30 days
7
29% of all-time downloads
olmo2-1b-rl-crosscoder
yashsawant22/olmo2-1b-rl-crosscoder
olmo2-1b-rl-crosscoder is a machine learning model from yashsawant22. 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 rl-crosscoder. The card lists the license as mit.
A TopK crosscoder trained on paired residual-stream activations of allenai/OLMo-2-0425-1B-DPO and allenai/OLMo-2-0425-1B-RLVR1 to study which features the RL step modifies. Shared encoder, per-model decoders, k=64 act…
All-time downloads
24
Public
Repo size
268 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt268 MB · 100%
At a glance
- Library
- rl-crosscoder
- License
- mit
- Access
- Public
- Created
- Aug 2, 2026
- Updated
- Aug 2, 2026
- SHA
- 91a3423a
Model card
From the Hugging Face model README
OLMo-2-1B DPO→RLVR1 crosscoder (layer 12, TopK k=64)
A TopK crosscoder trained on paired residual-stream activations of allenai/OLMo-2-0425-1B-DPO
and allenai/OLMo-2-0425-1B-RLVR1 to study which features the RL step modifies. Shared encoder,
per-model decoders, k=64 active features/token, d_hidden=8192. FVE ≈ 0.87.
Finding: the features RL modifies most are ~2× more reasoning-selective than the ones it leaves alone (corr +0.25), while the full SFT+DPO+RL pipeline points the opposite way — the reasoning- targeting is specific to the RL step. Code + write-up: https://github.com/yash-sawant/rl-crosscoder
from rl_crosscoder.crosscoder import Crosscoder
cc = Crosscoder.from_pretrained("Savianto/olmo2-1b-rl-crosscoder", filename="crosscoder.pt")
- Library
- rl-crosscoder
- License
- mit
- Created
- Aug 2, 2026
- Updated
- Aug 2, 2026