© 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 EvalsExportsAPI 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. 18185
    Prev
    Next
    INDEX
    Explanations

    sports-related terms, especially related to soccer matches

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    714
    +0.10
    0.5%
    718
    +0.10
    0.4%
    542
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    714
    +0.10
    0.01
    170
    +0.10
    0.02
    312
    +0.09
    0.01
    Negative Logits
    ãĥ¤
    -0.80
    jon
    -0.71
    rh
    -0.71
    BILITIES
    -0.70
    onom
    -0.70
    Sov
    -0.69
    lihood
    -0.69
    rets
    -0.69
    ibles
    -0.68
    nos
    -0.68
    POSITIVE LOGITS
     alike
    0.78
     successive
    0.74
     endlessly
    0.74
     until
    0.73
     bombard
    0.72
     thereafter
    0.72
     relentlessly
    0.72
     throughout
    0.72
     accumulate
    0.71
     consecut
    0.68
    Activations Density 0.026%

    No Known Activations