© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 3837
    Prev
    Next
    INDEX
    Explanations

    ingredients or components used in the preparation of recipes

    oai_token-act-pair · gpt-3.5-turbo

    key components of recipes, narratives, and descriptions involving organizations or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sent
    -0.65
    )-
    -0.65
    ulative
    -0.63
     Franch
    -0.63
    )",
    -0.63
     Hers
    -0.61
     Meridian
    -0.60
     Kend
    -0.60
    ilater
    -0.60
    ioch
    -0.59
    POSITIVE LOGITS
    enegger
    0.83
    BILITY
    0.70
     goddamn
    0.69
    reated
    0.64
    BAT
    0.60
    Arcade
    0.59
    $$$$
    0.58
    !".
    0.58
    ructose
    0.58
    tumblr
    0.58
    Activations Density 0.429%

    No Known Activations