Transformer Lens Interpretability
Skill Verified ActiveProvides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
To empower researchers and practitioners to deeply inspect and manipulate transformer model internals for mechanistic interpretability studies using the TransformerLens library.
Features
- Inspect and manipulate transformer internals via HookPoints
- Perform activation caching and patching experiments
- Analyze attention patterns and information flow
- Reverse-engineer learned model algorithms
- Support for 50+ transformer models including LLaMA and Mistral
Use Cases
- Reverse-engineering algorithms learned by transformer models
- Performing activation patching and causal tracing experiments
- Studying attention patterns and information flow within models
- Analyzing specific circuits like induction heads or IOI circuits
Non-Goals
- Working with non-transformer architectures
- Training or analyzing Sparse Autoencoders
- Remote execution on massive models requiring specialized infrastructure
- Higher-level causal intervention abstractions better suited to other libraries
Installation
First, add the marketplace
/plugin marketplace add Orchestra-Research/AI-Research-SKILLs/plugin install AI-Research-SKILLs@ai-research-skillsQuality Score
VerifiedTrust Signals
Similar Extensions
TransformerLens Mechanistic Interpretability
95Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
Embedding Strategies
100Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
Aws Cdk Development
100AWS Cloud Development Kit (CDK) expert for building cloud infrastructure with TypeScript/Python. Use when creating CDK stacks, defining CDK constructs, implementing infrastructure as code, or when the user mentions CDK, CloudFormation, IaC, cdk synth, cdk deploy, or wants to define AWS infrastructure programmatically. Covers CDK app structure, construct patterns, stack composition, and deployment workflows.
Fit Drift Diffusion Model
100Fit cognitive drift-diffusion models (Ratcliff DDM) to reaction time and accuracy data with parameter estimation (drift rate, boundary separation, non-decision time), model comparison, and parameter recovery validation. Use when modeling binary decision-making with reaction time data, estimating cognitive parameters from experimental data, comparing sequential sampling model variants, or decomposing speed-accuracy tradeoff effects into latent cognitive components.
Ui Ux Pro Max
100UI/UX design intelligence with searchable style, palette, typography, and chart databases. Use when designing UI components, choosing colors/fonts, reviewing code for UX issues, building landing pages, or implementing responsive layouts.
Google Tts
100Convert documents and text to audio using Google Cloud Text-to-Speech. Use this skill when the user wants to: narrate a document, read aloud text, generate audio from a file, convert text to speech, create a recording of documentation or analysis, create a podcast from a document, or use Google TTS/text-to-speech. Trigger phrases: "read this aloud", "narrate this", "create a recording", "text to speech", "TTS", "convert to audio", "audio from document", "listen to this", "generate audio", "google tts", "create a podcast".