© 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. 1-RES-JB
    11. 438
    Prev
    Next
    INDEX
    Explanations

    descriptions related to sports, specifically soccer plays and strategies

    oai_token-act-pair · gpt-3.5-turbo

    references to sports actions and gameplay

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.77
    Actor
    -0.75
    yll
    -0.74
    verified
    -0.63
    wcsstore
    -0.63
     Loans
    -0.62
    ĨĴ
    -0.62
    afort
    -0.61
    anson
    -0.61
     Stevens
    -0.61
    POSITIVE LOGITS
     alley
    0.90
     formation
    0.83
     earthqu
    0.79
     flank
    0.78
     defenders
    0.77
     horizont
    0.73
     defender
    0.72
    ãĥ¼ãĥ³
    0.71
     opponent
    0.71
     hole
    0.69
    Activations Density 0.801%

    No Known Activations