© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 20810
    Prev
    Next
    INDEX
    Explanations

    keywords related to governmental positions and organizations

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to disease or secretive activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WARD
    -0.72
    seys
    -0.69
    MER
    -0.68
    sol
    -0.66
    WAR
    -0.65
     Pilgrim
    -0.63
    @#&
    -0.63
    arious
    -0.63
    porary
    -0.62
    nuts
    -0.62
    POSITIVE LOGITS
    mble
    0.97
    ly
    0.89
    ague
    0.77
    uve
    0.73
    yu
    0.71
     Dise
    0.69
     Franch
    0.67
    ño
    0.67
    lement
    0.66
    velt
    0.65
    Activations Density 0.019%

    No Known Activations