Spaces:
Running
Running
Commit History
-
Tutorial, feedback, and github buttons added
e1f91c2
-
Fixed slider loading bug
4416500
-
Moved glossary button to header instead of hidden in sidebar
42ae447 -
fixed ablation bug, ablated output was shown in pipeline
96418df
-
Added simpler ablation experiment buttons to add full categories
3c5f2fd -
Added pre-built prompts for app and chatbot
018a9f2
-
Bug fix: type issue with models leading to gibberish outputs
5528a77
-
Reduce jargon across UI for younger/less-technical audiences
Replace technical ML terminology with plain-English equivalents while preserving technical terms as parentheticals for educational value: - Tokenization → Text Splitting - Embedding/vector → Meaning Encoding/list of numbers - MLP (Feed-Forward) → Knowledge Retrieval - Ablation → Test by Removing - Token Attribution → Word Influence - Attention heads → detectors (with "heads" as technical note) - Activation score → activity level - Probability shift → confidence change Updated glossary entries to lead with friendly names. Chatbot suggestions also updated for consistency. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>abf6a1c
-
Fixed chatbot bubble generation bug
d075209 -
Fixed single-token sequence UI bug
e248349 -
Fixed ablation original prompt generation bug
1356785 -
Fixed ablation graphs first token population, still need to fix original graphs when no beam selected
cb213d9 -
Fixed ablation graphs first token population, still need to fix original graphs when no beam selected
670d882
-
Fixed model-switching bug with activation store clearing
7ad3e7b
-
Added loading screen to pipeline steps for better UX
93c55d0 -
completed the rest of the explanation improvements from JARVIS audit
ff1ba74
-
Attention refactor, better categorization and explanation
7fa8fb4
-
Fixed glossary UI to be cleaner
1cce926
-
Chatbot improvements: UI cleaning, chat streaming, typing animation, and better markdown formatting
a684a8d -
ablation experiment fixes, better UI and full sequence comparison
a938eeb
-
feat(output): Add token scrubber with per-position top-5 next-token probabilities
Co-authored-by: Cursor <cursoragent@cursor.com>d60cfe2 -
Added full sequence to analysis, still need to do output scrubber
3f991b4
-
Add Dockerfile for Hugging Face Spaces deployment
159696b
-
Added message greeting to chatbot
b6266bb
-
cleanup stuff
1f487a9 -
Migrate from Gemini to OpenRouter API
Co-authored-by: Cursor <cursoragent@cursor.com>ef3e36a -
Add Hugging Face deployment prep: .gitignore, load_dotenv, API tests
Co-authored-by: Cursor <cursoragent@cursor.com>689669f -
Resolve merge conflicts in README.md and todo.md
Co-authored-by: Cursor <cursoragent@cursor.com>b4d0227 -
feat: Add AI chatbot with Gemini integration and RAG support
Co-authored-by: Cursor <cursoragent@cursor.com>62884e7 -
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 -
conductor setup
aabd66e
-
conductor(checkpoint): Checkpoint end of Phase 3: Visualization & Feedback Loop
72f82a4 -
conductor(checkpoint): Checkpoint end of Phase 2: Frontend Control Panel
24bd049 -
Fix multi-layer ablation to ablate all heads simultaneously
ae08976
-
Fix ablation head selection: handle old data format, prevent spurious selections on render
bb577e6 -
Fix 5 UI issues: comparison button, tokenization layout, expandable attention categories, BertViz instructions, multi-layer ablation
0f46e9c -
Refactor analysis scope and enhance attention UI (Agents F and G)
8a1fc4b -
Improve UI clarity: rename generation settings labels and remove score display
d134e9a
-
Refactor: Replace heatmap with pipeline explanation visualization
3850656 -
Fix heatmap colorbar config
5261108 -
heatmap implementation
ac745db
-
Ablation updated for full sequence, needs refactor for front-end and workflow
2ad1c2e
-
Fixed errors for beam search refactor
c19d5a8
-
Fix storage quota error by using memory storage and add type safety checks
cc96787
-
Better explanations, moved transformer layer diagram to be more visible
080932d
-
Fix: Add actual_output to session store to display final token and highlight significant layers
CRITICAL FIX resolving two related issues: 1. Final output token not being displayed after graphs - Root cause: 'actual_output' was missing from essential_data in run_analysis callback - Impact: _create_actual_output_display() returned None, no output shown - Fix: Added 'actual_output': activation_data.get('actual_output') to essential_data 2. Layers not being highlighted despite >100% probability increases - Root cause: Same missing 'actual_output' field - Impact: detect_significant_probability_increases() couldn't find actual_output_token, returned empty list - Fix: Same addition of 'actual_output' to essential_data The try-catch in execute_forward_pass was working correctly - it successfully computed actual_output and global_top5_tokens. The bug was that this computed data was being discarded when creating essential_data for the session store. Applied fix to both essential_data (prompt 1) and essential_data2 (prompt 2). Testing confirmed: - Actual output now d…4c6777d -
Update layer highlighting to 100% threshold for actual output token only
- Changed detect_significant_probability_increases to only check actual output token instead of all top 5 tokens - Updated threshold from 50% to 100% (doubled probability) for highlighting layers - Modified compute_layer_wise_summaries to accept activation_data and extract actual output token - Updated all calls to compute_layer_wise_summaries in app.py to pass activation_data - Added _create_actual_output_display helper function to show actual model output - Display actual output token below final output graphs (normal mode, ablation mode, comparison mode) - Added tooltip explaining why actual output may differ from highest probability token in final layer due to residual connections - Updated graph tooltip text to reflect 100% threshold change9d22c3c
-
Improve explanations: optimize head categorization and comparison thresholds, enhance ablation explanation, rewrite all tooltips for high school level
b828e58 -
Clean up: fix significant layer threshold to 50%, remove unused logit lens parameter, remove certainty calculations
a4e6de8
-
Add ablation experiment before/after comparison with Reset button
- Added session-activation-store-original to preserve pre-ablation data - Modified run_head_ablation callback to save original data before ablation - Updated create_layer_accordions to detect ablation mode and show before/after sections for all layers - Modified _create_single_prompt_chart and _create_token_probability_delta_chart to accept title suffixes - Added before/after comparison for line graphs showing top 5 token probabilities across layers - Added Reset Ablation button in sidebar (visible only during ablation) - Implemented reset_ablation callback to restore original data and clear ablation - Added visual polish with section headers, background colors (blue for before, orange for after), and explanatory tooltips - All changes maintain backward compatibility with non-ablation moded701d46