Spaces:
Running
Running
Commit History
-
Fixed ablation experiments, drilled down on which pre-loaded ones to run
3d71d04
-
Bug fix: type issue with models leading to gibberish outputs
5528a77
-
Attention refactor, better categorization and explanation
7fa8fb4
-
feat(output): Add token scrubber with per-position top-5 next-token probabilities
Co-authored-by: Cursor <cursoragent@cursor.com>d60cfe2
-
chore: remove unused code, imports, and deprecated functions
- Delete components/tokenization_panel.py (superseded by pipeline.py) - Remove 6 unused imports from app.py - Remove deprecated _get_top_attended_tokens() and references - Remove unused create_stage_summary() from pipeline.py - Remove 7 unused utility functions from model_patterns.py and beam_search.py - Update utils/__init__.py exports and README.md Total: ~1,087 lines removed. All 81 tests pass. Co-authored-by: Cursor <cursoragent@cursor.com>2965a7d
-
fix(utils): Export generate_bertviz_model_view_html from package
5cad664 -
Fix multi-layer ablation to ablate all heads simultaneously
ae08976
-
Switch attention viz to head_view and add categorization (Agent D)
ef749ae
-
Refactor: Replace heatmap with pipeline explanation visualization
3850656 -
heatmap implementation
ac745db
-
Ablation updated for full sequence, needs refactor for front-end and workflow
2ad1c2e
-
Fix storage quota error by using memory storage and add type safety checks
cc96787
-
Phase 1: Backend infrastructure for token merging, layer-wise tracking, and head ablation
- Added merge_token_probabilities() to sum probabilities of tokens with/without leading space - Added compute_global_top5_tokens() to get top 5 from final model output - Updated logit_lens_transformation() to return merged probabilities - Updated get_check_token_probabilities() to sum token variant probabilities - Added detect_significant_probability_increases() to find layers with >=25%% relative increase - Added _get_token_probabilities_for_layer() helper for tracking specific tokens - Updated extract_layer_data() to track global top 5 across all layers with deltas - Added compute_layer_wise_summaries() to create convenient summary structures - Added execute_forward_pass_with_head_ablation() to zero out specific attention heads - Updated execute_forward_pass() and execute_forward_pass_with_layer_ablation() to include global_top5_tokens - All functions exported and properly integratedac1a7df
-
completed ablation experiment implementation
65dd6b7
-
Fix accordion data flow and remove all legacy Cytoscape code
- Fixed root cause: Added missing fields (block_modules, block_outputs, logit_lens_parameter, norm_parameters) to session-activation-store - Removed all Cytoscape visualization code and components - Removed unused functions: format_data_for_cytoscape, _create_node, _create_edge, _highlight_divergent_layers, token_to_color, and edge tooltip callbacks - Simplified callback signatures and return values - Cleaned up imports (removed dash_cytoscape) - Updated main_panel.py to show only accordion-based layer view - Accordions now populate correctly with layer predictions44b60b5 -
Replace Cytoscape with accordion-based layer view
- Added html.Details/Summary accordion panels for each layer - Display plain-language headers: 'Layer L{N}: likely {token} (p={prob})' - Added token chips showing top-3 predictions between layers - Gated old Cytoscape graph behind USE_LEGACY_CYTOSCAPE feature flag - Added CSS for accordion styling with ellipsis truncation - Created extract_layer_data() utility function - All panels closed by default for compact flow view5c05f37
-
Refactor Check Token: Replace 4th edge with probability line graph
431ab15
-
Fix: Export categorize_single_layer_heads from utils package
d2086cb
-
Feature update: Reorganize attention head categorization with BertViz visualizations for each category
8e9f963 -
Feature 6: Implement two-prompt difference analysis with divergent layer highlighting
55e225f -
Feature 5: Implement attention head detection and categorization with visual display
24b78dc
-
Added model config for automatic model parameter detection
c6cb681
-
Full visualization reorganization, handles model selection, parameter selection, visualizes graphs w/ bertviz onclick
1a93ca4