© 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. 10-RES-JB
    11. 18954
    Prev
    Next
    INDEX
    Explanations

    mentions of American football plays and actions

    oai_token-act-pair · gpt-3.5-turbo

    key terms and actions related to sports plays and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     outfits
    -0.76
     organisations
    -0.75
     acron
    -0.73
     evenings
    -0.70
     winters
    -0.69
    indust
    -0.69
    urers
    -0.68
     modelling
    -0.68
    rooms
    -0.67
     belts
    -0.67
    POSITIVE LOGITS
     fumble
    1.29
     touchdown
    1.12
     timeout
    1.10
     punt
    1.08
     interception
    1.03
     Penalty
    0.98
     intercepted
    0.91
     interference
    0.90
     foul
    0.89
     ensuing
    0.88
    Activations Density 0.268%

    No Known Activations