Skip to content

Refactor clustering to use compressed memberships #456

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ocg-goodfire wants to merge 5 commits into
base: dev
Choose a base branch
from
Open

Refactor clustering to use compressed memberships #456

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
124316f
Refactor clustering to use compressed memberships
ocg-goodfire Mar 18, 2026
8483070
Speed up clustering merge benchmarks
ocg-goodfire Mar 18, 2026
ac99c0e
Speed up exact clustering overlap updates
ocg-goodfire Mar 18, 2026
dd72fab
Simplify exact clustering merge path
ocg-goodfire Mar 18, 2026
a4db390
Add configurable clustering dead-filter stat
ocg-goodfire Mar 19, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,8 +34,9 @@ dependencies = [
"aiolimiter>=1.2",
"openrouter>=0.1.1",
"httpx>=0.28.0",
"zstandard", # For streaming datasets
"zstandard", # For streaming datasets
"kaleido==0.2.1",
"numba>=0.64.0",
]

[dependency-groups]
Expand Down
2 changes: 1 addition & 1 deletion spd/clustering/CLAUDE.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,7 +80,7 @@ Computes pairwise distances between clustering runs in an ensemble:
```python
ClusteringPipelineConfig # Pipeline settings (n_runs, distances_methods, SLURM config)
ClusteringRunConfig # Single run settings (model_path, batch_size, n_tokens, merge_config)
MergeConfig # Merge algorithm params (alpha, iters, activation_threshold)
MergeConfig # Merge algorithm params (alpha, iters, activation_threshold, filter_dead_stat)
```

### Data Structures
Expand Down
Loading