Features

Explore nnsight's capabilities in depth through interactive notebooks.

Core Features

• Getting Activations - Access hidden states and activations from any layer
• Setting Activations - Modify activations to study causal effects
• Gradients - Compute gradients with respect to intermediate values
• Multiple Token Generation - Work with autoregressive generation
• Module Access - Navigate and access model components
• Model Editing - Create persistent model modifications
• Cross-Prompt Intervention - Transfer activations between different prompts
• Empty Invokers - Run interventions without input data
• Intermediate Operations - Access intermediate operations inside modules
• Early Stopping - Stop computation early for efficiency
• Skip Execution - Skip parts of model execution
• Scan - Infer shapes without full execution
• Remote Execution - Run on NDIF's remote infrastructure
• Streaming - Stream outputs during generation
• vLLM Support - High-performance inference with vLLM