© 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. 8-RES-JB
    11. 1178
    Prev
    Next
    INDEX
    Explanations

    words related to places and names, likely geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    components related to mythology and ancient symbolism

    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
    enhagen
    -0.73
    é¾įå
    -0.73
     prosecut
    -0.64
    omnia
    -0.64
    creen
    -0.64
     crowds
    -0.64
    liners
    -0.62
     crowd
    -0.61
    PsyNetMessage
    -0.61
     smugg
    -0.59
    POSITIVE LOGITS
    lain
    0.85
    leon
    0.79
    ynski
    0.78
    jee
    0.76
    anooga
    0.75
    obos
    0.75
     Lumpur
    0.74
    zyk
    0.74
    jong
    0.71
    ivari
    0.70
    Activations Density 0.168%

    No Known Activations