Quickstart¶
Install¶
pip install reptimeline
Command-Line Usage¶
# Track specific concepts across training checkpoints
python -m reptimeline \
--checkpoint-dir checkpoints/ \
--concepts king queen love hate
# Full analysis with all 63 primitives, overlay, and plots
python -m reptimeline \
--checkpoint-dir checkpoints/ \
--primitives --overlay --plot \
--max-checkpoints 8 \
--output timeline.json
Python API¶
from reptimeline import TimelineTracker, TriadicExtractor
# 1. Extract representations from checkpoints
extractor = TriadicExtractor()
concepts = ["king", "queen", "love", "hate", "dog", "cat"]
snapshots = extractor.extract_sequence("checkpoints/", concepts)
# 2. Analyze evolution
tracker = TimelineTracker(extractor)
timeline = tracker.analyze(snapshots)
# 3. Inspect results
timeline.print_summary()
# Births: 2632, Deaths: 1732, Connections: 1378, Phase transitions: 3
Visualization¶
from reptimeline.viz import plot_phase_dashboard, plot_churn_heatmap
plot_phase_dashboard(timeline, save_path="phase.png")
plot_churn_heatmap(timeline, save_path="churn.png")
See Visualization for all 4 plot types.
Bottom-Up Discovery¶
No labels needed -- discover what the model learned:
from reptimeline.discovery import BitDiscovery
discovery = BitDiscovery()
report = discovery.discover(snapshots[-1], timeline=timeline)
discovery.print_report(report)
# Discovers: bit semantics, dual pairs, dependencies, 3-way interactions
See Discovery Pipeline for the full pipeline.
Next Steps¶
- Architecture -- understand the 4-layer design
- Discovery Pipeline -- full bottom-up ontology discovery
- Visualization -- all plot types with examples
- API Reference -- complete module documentation