© 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. 10-RES-JB
    11. 18977
    Prev
    Next
    INDEX
    Explanations

    news and political entities

    oai_token-act-pair · gpt-3.5-turbo

    references to political candidates and their relevant statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uminati
    -0.87
    DragonMagazine
    -0.70
    ????????
    -0.69
     Nicarag
    -0.66
     externalToEVAOnly
    -0.65
    rious
    -0.64
    farious
    -0.64
    Translation
    -0.62
    soType
    -0.61
     Canaver
    -0.61
    POSITIVE LOGITS
     fared
    1.65
     accounted
    1.59
     averaged
    1.59
     outper
    1.47
     ranked
    1.35
     scored
    1.33
     trailed
    1.32
     surpassed
    1.31
     totaled
    1.29
     averages
    1.27
    Activations Density 0.426%

    No Known Activations