© 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. 11-RES-JB
    11. 3383
    Prev
    Next
    INDEX
    Explanations

    references to specific anatomical body parts, specifically the upper body

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "upper" or "upper body."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagen
    -0.75
    tnc
    -0.74
     Chaser
    -0.74
    ulously
    -0.73
    naire
    -0.72
    oris
    -0.72
    terday
    -0.70
    atile
    -0.67
    hots
    -0.64
    76561
    -0.64
    POSITIVE LOGITS
    most
    1.05
    class
    0.95
     tiers
    0.92
    case
    0.87
     tier
    0.85
     floors
    0.83
     crust
    0.82
     reaches
    0.82
     Midwest
    0.82
     extrem
    0.81
    Activations Density 0.045%

    No Known Activations