© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 4124
    Prev
    Next
    INDEX
    Explanations

    references to livelihoods and specific organizations or individuals like Woody Guthrie

    oai_token-act-pair · gpt-3.5-turbo

    references to significant individuals and their impacts on livelihood or production

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

    No Comments

    Negative Logits
    upt
    -0.86
     Sed
    -0.74
    ames
    -0.74
    VILLE
    -0.73
    ãģ®æ
    -0.69
    anders
    -0.65
    -+
    -0.65
    ocial
    -0.65
    fitted
    -0.64
    GW
    -0.64
    POSITIVE LOGITS
    earance
    0.89
    inez
    0.82
    ierrez
    0.80
    licted
    0.79
    isher
    0.78
    ersen
    0.77
    yip
    0.76
    enhagen
    0.75
     subp
    0.74
    ornia
    0.74
    Activations Density 0.037%

    No Known Activations