© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 9-ATT_32K-OAI
    gpt2-small · 9-att_32k-oai
    Source from gpt2sm-oai-2024 · Attention Out - 32k · Layer 9
    Jump to Source/SAE
    Jump to Feature
    INDEX

    Configuration

    jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_9
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.9.hook_attn_out
    Hook Layer
    9
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk

    Search via Inference

    Run Example Search

    Search TopK by Token

    0%
    1%
    10%
    100%

    Search Explanations

    Browse

    Features in GPT2-SMALL@9-att_32k-oai
    1. Hover over a feature on the left to preview its details.
    2. Click a feature to lock it and interact with it.