© 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. 12220
    Prev
    Next
    INDEX
    Explanations

    mentions of American football terminology, specifically related to the offensive side of the game

    oai_token-act-pair · gpt-3.5-turbo

    terms related to offensive coordination in sports, particularly football

    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
    ioxide
    -0.75
    bourg
    -0.75
     Solitaire
    -0.74
    bush
    -0.72
    atar
    -0.71
    DAY
    -0.70
    neys
    -0.70
    asta
    -0.69
    aiman
    -0.68
    hyde
    -0.68
    POSITIVE LOGITS
     linemen
    1.05
     lineman
    0.94
     coordinator
    0.94
     firepower
    0.80
     LINE
    0.77
     outburst
    0.76
     coordin
    0.74
     line
    0.74
    scill
    0.74
    orically
    0.72
    Activations Density 0.045%

    No Known Activations