© 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 · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 22822
    Prev
    Next
    INDEX
    Explanations

    mentions of the Edmonton Oilers and related teams

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    481
    +0.14
    0.7%
    267
    +0.11
    0.5%
    201
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    201
    +0.14
    0.02
    612
    +0.11
    0.02
    500
    +0.11
    0.02
    Negative Logits
    colo
    -0.87
    stakes
    -0.84
    strate
    -0.76
    sole
    -0.75
    fortune
    -0.71
    milo
    -0.70
    uku
    -0.69
    efully
    -0.67
    foot
    -0.67
    creen
    -0.67
    POSITIVE LOGITS
     Oilers
    1.37
    monton
    1.01
     Esk
    0.99
    shire
    0.92
     Rapids
    0.80
    atoon
    0.79
    rador
    0.74
     Municip
    0.73
    ians
    0.72
     Province
    0.72
    Activations Density 0.027%

    No Known Activations