© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 17271
    Prev
    Next
    INDEX
    Explanations

    words related to various sports, especially football (both American football and soccer)

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports, specifically football and soccer

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

    No Comments

    Negative Logits
    shapeshifter
    -0.70
     inexper
    -0.69
     flawless
    -0.65
     experienced
    -0.65
    lishes
    -0.63
     inexperienced
    -0.62
     compe
    -0.61
     coma
    -0.61
     insane
    -0.61
    reading
    -0.61
    POSITIVE LOGITS
     soccer
    0.83
     stadiums
    0.81
    hof
    0.79
     basketball
    0.79
     rugby
    0.78
     volleyball
    0.77
    nell
    0.75
     hockey
    0.74
     stadium
    0.74
     baseball
    0.74
    Activations Density 0.267%

    No Known Activations