README
Continuation control
40/40 GO→EOS
40/40 EOS→GO
640/640 controls unchanged
Prompt, weights, and generated reasoning prefix held fixed during intervention.
Rayan Pal
getswiftapi.com
Independent Researcher
Thinking-enabled PCCG-Qwen3-4B with an equality-conditioned continuation policy. One fixed 2,560-dimensional activation direction at block 29, applied after the model generated </think>. Intervention strength: 2.0. GO is followed by native EOS.
| Confirmation measurement | Result |
|---|---|
| Correct generated comparison trace and answer | 80/80 |
| Unmodified replay | 80/80 |
| GO→EOS | 40/40 |
| EOS→GO | 40/40 |
| Controls unchanged | 640/640 |
Anthropic's Jacobian Lens provides internal vocabulary readouts. Additive activation interventions measure causal effects. Method.
Verify
Clone with Git LFS installed. The fitted lens is stored in Git LFS.
git lfs pull
python verify.py
Checks package hashes and recounts the confirmation records. Runs on CPU using the Python standard library.
Reproduce
Commands and model requirements.
Contents
results/: complete study records, logits, activations, fitted lens, and fixed direction.source/: executed study code and Anthropic's Jacobian Lens implementation.protocol/: prompts, case sets, model qualification record, and reproduction settings.SHA256SUMS: package file hashes.LICENSE: Apache 2.0. The vendored implementation retains its license insource/vendor/LICENSE.
Contributors
1 commits
See what people are saying
Similar repos
Languages
Python
100.0%
README
Continuation control
40/40 GO→EOS
40/40 EOS→GO
640/640 controls unchanged
Prompt, weights, and generated reasoning prefix held fixed during intervention.
Rayan Pal
getswiftapi.com
Independent Researcher
Thinking-enabled PCCG-Qwen3-4B with an equality-conditioned continuation policy. One fixed 2,560-dimensional activation direction at block 29, applied after the model generated </think>. Intervention strength: 2.0. GO is followed by native EOS.
| Confirmation measurement | Result |
|---|---|
| Correct generated comparison trace and answer | 80/80 |
| Unmodified replay | 80/80 |
| GO→EOS | 40/40 |
| EOS→GO | 40/40 |
| Controls unchanged | 640/640 |
Anthropic's Jacobian Lens provides internal vocabulary readouts. Additive activation interventions measure causal effects. Method.
Verify
Clone with Git LFS installed. The fitted lens is stored in Git LFS.
git lfs pull
python verify.py
Checks package hashes and recounts the confirmation records. Runs on CPU using the Python standard library.
Reproduce
Commands and model requirements.
Contents
results/: complete study records, logits, activations, fitted lens, and fixed direction.source/: executed study code and Anthropic's Jacobian Lens implementation.protocol/: prompts, case sets, model qualification record, and reproduction settings.SHA256SUMS: package file hashes.LICENSE: Apache 2.0. The vendored implementation retains its license insource/vendor/LICENSE.
See what people are saying
Similar repos
Contributors
1 commits
Languages
Python
100.0%