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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 6822
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ecycle
    -0.72
    uming
    -0.70
    utsche
    -0.70
     Deutsche
    -0.69
    ucer
    -0.66
    uding
    -0.66
    jriwal
    -0.65
     lungs
    -0.65
    ersen
    -0.65
    gow
    -0.64
    POSITIVE LOGITS
     Noir
    0.73
    pmwiki
    0.71
    FontSize
    0.66
     pandemonium
    0.61
     Palest
    0.61
     Pell
    0.61
     ANGEL
    0.60
     tem
    0.60
    Ń·
    0.59
    sic
    0.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.