# Reasoning Trajectories Glossary

Terms used in the reasoning-trajectory codebase and HF Spaces deployment.

## Terms

**Trajectory**:
The path through representation space traced by a model's hidden states across chain-of-thought reasoning tokens.
_Avoid_: Path, chain

**Step marker**:
A "Step N:" token in generated CoT text that delimits individual reasoning steps. Detected by matching token ID 8468 in the sequence.
_Avoid_: Boundary, delimiter

**dp1 / dp2**:
Decision points — dp1 is the first generated token after the prompt (start of reasoning), dp2 is the start of the final answer after the `####` marker.
_Avoid_: Start/end point

**Logit lens**:
Projecting each layer's hidden state through the unembedding matrix (W_U) to interpret what the model predicts at every layer, not just the final one.
_Avoid_: Early decoding, probing

**Two-pass generation**:
Optimization: first pass generates with KV cache (no capture), second pass runs a single forward through the full sequence to capture all per-timestep hidden states and logits at once.
_Avoid_: Two-stage

**HF Space**:
A Hugging Face-hosted web application (Gradio, Streamlit, or Docker) that runs ML demos. Configured via README.md frontmatter.
_Avoid_: Space, HF app

**TinyLlama-1.1B-Chat**:
A 1.1B parameter open-source LLM based on Llama 2, small enough to run on CPU. Used as our demonstration model.
_Avoid_: TL, Tiny