SRT introspect
🧭
Adaptive-density reasoning traces over a frozen Qwen-2.5-7B
River Rider PRO
RiverRider
AI & ML interests
Computational semiotics is empirically proven. It takes three to tango 💃🪩🕺
Recent Activity
updated a Space about 16 hours ago
RiverRider/srt-introspect published a Space about 16 hours ago
RiverRider/srt-introspect reacted to theirpost with 👀 1 day ago
A single forward pass of the frozen Qwen-2.5-7B model plus a lightweight classifier reaches 0.866 plus or minus 0.011 AUC on the full TruthfulQA-MC2 benchmark. No adapters. No fine-tuning. No extra parameters on the backbone.
This is the strongest hidden-state truthfulness detector reported on the benchmark to date.
The same latent features that the SRT-NLA-AV-v1 demo reads out as coherent natural-language verbalizations turn out to be rich enough to support production-grade auditing for honesty versus hallucination. The internal semiotic infrastructure we have been exploring in public is already information-dense enough to solve hard downstream problems with almost trivial overhead.
You can watch the underlying latent geometry in action right here:
https://huggingface.co/spaces/RiverRider/srt-nla-av-v1-demo
Full code, artifacts, and reproduction steps are in the repository:
https://github.com/space-bacon/SRT
Try the Glass Box
https://huggingface.co/spaces/RiverRider/srt-nla-demoOrganizations
updated a
Space about 16 hours ago
published a
Space about 16 hours ago
reacted to their post with 👀 1 day ago
Post
181
A single forward pass of the frozen Qwen-2.5-7B model plus a lightweight classifier reaches 0.866 plus or minus 0.011 AUC on the full TruthfulQA-MC2 benchmark. No adapters. No fine-tuning. No extra parameters on the backbone.
This is the strongest hidden-state truthfulness detector reported on the benchmark to date.
The same latent features that the SRT-NLA-AV-v1 demo reads out as coherent natural-language verbalizations turn out to be rich enough to support production-grade auditing for honesty versus hallucination. The internal semiotic infrastructure we have been exploring in public is already information-dense enough to solve hard downstream problems with almost trivial overhead.
You can watch the underlying latent geometry in action right here:
RiverRider/srt-nla-av-v1-demo
Full code, artifacts, and reproduction steps are in the repository:
https://github.com/space-bacon/SRT
Try the Glass Box
RiverRider/srt-nla-demo
This is the strongest hidden-state truthfulness detector reported on the benchmark to date.
The same latent features that the SRT-NLA-AV-v1 demo reads out as coherent natural-language verbalizations turn out to be rich enough to support production-grade auditing for honesty versus hallucination. The internal semiotic infrastructure we have been exploring in public is already information-dense enough to solve hard downstream problems with almost trivial overhead.
You can watch the underlying latent geometry in action right here:
RiverRider/srt-nla-av-v1-demo
Full code, artifacts, and reproduction steps are in the repository:
https://github.com/space-bacon/SRT
Try the Glass Box
RiverRider/srt-nla-demo
posted an update 5 days ago
Post
181
A single forward pass of the frozen Qwen-2.5-7B model plus a lightweight classifier reaches 0.866 plus or minus 0.011 AUC on the full TruthfulQA-MC2 benchmark. No adapters. No fine-tuning. No extra parameters on the backbone.
This is the strongest hidden-state truthfulness detector reported on the benchmark to date.
The same latent features that the SRT-NLA-AV-v1 demo reads out as coherent natural-language verbalizations turn out to be rich enough to support production-grade auditing for honesty versus hallucination. The internal semiotic infrastructure we have been exploring in public is already information-dense enough to solve hard downstream problems with almost trivial overhead.
You can watch the underlying latent geometry in action right here:
RiverRider/srt-nla-av-v1-demo
Full code, artifacts, and reproduction steps are in the repository:
https://github.com/space-bacon/SRT
Try the Glass Box
RiverRider/srt-nla-demo
This is the strongest hidden-state truthfulness detector reported on the benchmark to date.
The same latent features that the SRT-NLA-AV-v1 demo reads out as coherent natural-language verbalizations turn out to be rich enough to support production-grade auditing for honesty versus hallucination. The internal semiotic infrastructure we have been exploring in public is already information-dense enough to solve hard downstream problems with almost trivial overhead.
You can watch the underlying latent geometry in action right here:
RiverRider/srt-nla-av-v1-demo
Full code, artifacts, and reproduction steps are in the repository:
https://github.com/space-bacon/SRT
Try the Glass Box
RiverRider/srt-nla-demo
updated a
Space 6 days ago
reacted to their post with 🔥 6 days ago
Post
396
🧠 New Space: MindReader-NLA — ask a frozen LM what it's thinking, in plain English.
A trained Activation Verbalizer (~5–13M params, frozen backbone) over Qwen-2.5-7B, Llama-3.2-3B, and Gemma-2-2B. Three demos in one Space:
Playground — sample K verbalizations of the layer-L hidden state and score how well each reproduces the original activation when fed back through the same frozen model (raw + anisotropy-centred cosine FVE).
Live Thought Trace — stream a verbalization per token as the model writes, side-by-side with the generation.
Steer-by-Editing — edit the verbalized thought, project it back into hidden-state space, and watch the continuation change.
Runs on ZeroGPU. Try it: RiverRider/srt-nla-demo
Paper + code: https://github.com/space-bacon/SRT
A trained Activation Verbalizer (~5–13M params, frozen backbone) over Qwen-2.5-7B, Llama-3.2-3B, and Gemma-2-2B. Three demos in one Space:
Playground — sample K verbalizations of the layer-L hidden state and score how well each reproduces the original activation when fed back through the same frozen model (raw + anisotropy-centred cosine FVE).
Live Thought Trace — stream a verbalization per token as the model writes, side-by-side with the generation.
Steer-by-Editing — edit the verbalized thought, project it back into hidden-state space, and watch the continuation change.
Runs on ZeroGPU. Try it: RiverRider/srt-nla-demo
Paper + code: https://github.com/space-bacon/SRT
liked a
Space 6 days ago
posted an update 7 days ago
Post
396
🧠 New Space: MindReader-NLA — ask a frozen LM what it's thinking, in plain English.
A trained Activation Verbalizer (~5–13M params, frozen backbone) over Qwen-2.5-7B, Llama-3.2-3B, and Gemma-2-2B. Three demos in one Space:
Playground — sample K verbalizations of the layer-L hidden state and score how well each reproduces the original activation when fed back through the same frozen model (raw + anisotropy-centred cosine FVE).
Live Thought Trace — stream a verbalization per token as the model writes, side-by-side with the generation.
Steer-by-Editing — edit the verbalized thought, project it back into hidden-state space, and watch the continuation change.
Runs on ZeroGPU. Try it: RiverRider/srt-nla-demo
Paper + code: https://github.com/space-bacon/SRT
A trained Activation Verbalizer (~5–13M params, frozen backbone) over Qwen-2.5-7B, Llama-3.2-3B, and Gemma-2-2B. Three demos in one Space:
Playground — sample K verbalizations of the layer-L hidden state and score how well each reproduces the original activation when fed back through the same frozen model (raw + anisotropy-centred cosine FVE).
Live Thought Trace — stream a verbalization per token as the model writes, side-by-side with the generation.
Steer-by-Editing — edit the verbalized thought, project it back into hidden-state space, and watch the continuation change.
Runs on ZeroGPU. Try it: RiverRider/srt-nla-demo
Paper + code: https://github.com/space-bacon/SRT
published a
Space 7 days ago
updated a
dataset 7 days ago
published a
dataset 7 days ago
updated a
model 7 days ago
published a
model 7 days ago
updated a
dataset 7 days ago
published a
dataset 7 days ago
updated a
model 7 days ago
published a
model 7 days ago
replied to their post 8 days ago
It takes three to tango. 💃🪩🕺
updated a
Space 8 days ago
liked a
model 8 days ago