© 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. 6197
    Prev
    Next
    INDEX
    Explanations

    sports-related words, specifically related to soccer or football

    oai_token-act-pair · gpt-3.5-turbo

    sports-related statistics or scores

    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
     Cherokee
    -0.89
    uckland
    -0.82
     Dartmouth
    -0.81
    imore
    -0.80
    leigh
    -0.79
    ancock
    -0.77
    NZ
    -0.77
     Dominion
    -0.77
    wx
    -0.77
    entanyl
    -0.75
    POSITIVE LOGITS
     Messi
    1.90
     Juventus
    1.83
     Bayern
    1.81
     Madrid
    1.80
     Guardiola
    1.78
     Ronaldo
    1.77
     Barcelona
    1.77
     Dortmund
    1.57
     Serie
    1.56
     Liga
    1.53
    Activations Density 0.442%

    No Known Activations