sparse-autoencoder-training
SAELens: Sparse Autoencoders for Mechanistic Interpretability
SAELens is the primary library for training and analyzing Sparse Autoencoders (SAEs) - a technique for decomposing polysemantic neural network activations into sparse, interpretable features. Based on Anthropic's groundbreaking research on monosemanticity.
GitHub: jbloomAus/SAELens (1,100+ stars)
The Problem: Polysemanticity & Superposition
Individual neurons in neural networks are polysemantic - they activate in multiple, semantically distinct contexts. This happens because models use superposition to represent more features than they have neurons, making interpretability difficult.
SAEs solve this by decomposing dense activations into sparse, monosemantic features - typically only a small number of features activate for any given input, and each feature corresponds to an interpretable concept.
When to Use SAELens
Use SAELens when you need to:
- Discover interpretable features in model activations
- Understand what concepts a model has learned
- Study superposition and feature geometry
- Perform feature-based steering or ablation
More from firecrawl/ai-research-skills
pinecone
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
6prompt-guard
Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security.
6chroma
Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production clusters. Use for semantic search, RAG applications, or document retrieval. Best for local development and open-source projects.
6unsloth
Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization
5slime-rl-training
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
5mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform
5