Mechanistic experiments on how LLMs represent and compute arithmetic internally, with strict no-parser controls, reproducible audits, and an interactive article.
Hyperprobe is the Python implementation of the framework proposed in the paper "Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures".
Model forensics through geometry: residual-stream projections, activation traces, and attention routing.
Configurable character-level transformer training suite with built-in mechanistic interpretability toolkit — scale to 150M+ parameters and beyond, no ceilings, only hardware limits. Inspect attention weights, hidden states, and head specialisation across all layers. Documented circuit findings included.
Experimental Recurrent Residual Stream for GPT-2
Unsupervised latent-work and residual-stream interference profiling for language models
Lightweight residual-stream adapters for frozen LLMs: match LoRA at equal parameters, add inference-time steering, and run many behaviors per token on one small model for edge and local AI.
Empirical evidence for predictive coding tendencies in the GPT-2 family: residual stream convergence, activation patching, MLP transform analysis, zero-ablation, and logit lens across 7 languages.
Add a description, image, and links to the residual-stream topic page so that developers can more easily learn about it.
To associate your repository with the residual-stream topic, visit your repo's landing page and select "manage topics."