• Mechanistic Interp
• Openai sparse autoencoders
• Openai sparse autoencoder github
• Mech Interp
• Toy Models for Superposition
• Scaling monosemanticity with claude sonnet
• Decoding the Thought Vector
• Feature Visualization
• Curve Detectors
• Prism: mapping interpretable concepts and features in lanaguage latent space

• Llama3 SAE repo
• Transformer Lens