© 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. 20870
    Prev
    Next
    INDEX
    Explanations

    sports-related information, specifically mentions of sports organizations or events

    oai_token-act-pair · gpt-3.5-turbo

    references to sports

    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
    wcs
    -0.86
    arians
    -0.81
     sidel
    -0.70
    oys
    -0.69
    awaru
    -0.68
    ulner
    -0.66
    lessly
    -0.63
    ufact
    -0.63
    ishers
    -0.62
    yrinth
    -0.62
    POSITIVE LOGITS
     Illustrated
    0.86
    Center
    0.81
    Arizona
    0.74
    Business
    0.72
    Analysis
    0.71
    ribe
    0.71
    radio
    0.70
    Radio
    0.68
     Midwest
    0.68
    visor
    0.68
    Activations Density 0.027%

    No Known Activations