Python · Apache-2.0
Extraltodeus/J-Wash
Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.
★ 241
Stars
22 forks · 2 open issues
+4.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
33.5
Momentum / 100
see the breakdown below
3mo ago
Created
last push 2mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 3.8 | +4.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 12.9 | last week ran 1.86× the monthly pace |
| Freshness | 15 | 10.0 | last push 2mo ago; decays to zero at 180 days |
| Scale | 15 | 6.9 | 241 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 33.5 | sum of the above |
Detail
| Topics | abliterationaianthropicartificial-intelligencehuggingfaceinterpretabilityj-washjacobian-lenslarge-language-modelsllmmechanistic-interpretabilitymodel-editingneural-networkspytorchresearchsteeringtransformersvisualization |
| Matched on | LLM & Inference (large-language-models) |
| Short window | +4 stars over 7 days = 0.6/day |
| Long window | +8 stars over 26 days = 0.3/day |
| Lifetime average | 2.10 stars/day over 115 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |