© 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. 7479
    Prev
    Next
    INDEX
    Explanations

    information or details related to sports events and player activities

    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
    327
    +0.11
    0.5%
    481
    +0.10
    0.5%
    95
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    572
    +0.11
    0.06
    320
    +0.10
    0.04
    59
    +0.10
    0.04
    Negative Logits
    \.
    -0.71
     %%
    -0.71
    aqu
    -0.67
    buster
    -0.66
    estones
    -0.65
    merce
    -0.64
    bda
    -0.64
    Ê
    -0.63
    chwitz
    -0.62
    cycles
    -0.61
    POSITIVE LOGITS
     himself
    0.99
     his
    0.98
     fellow
    0.83
     teammate
    0.81
     unsuspecting
    0.80
     herself
    0.79
     opponents
    0.77
     passers
    0.76
     Himself
    0.74
     contemporaries
    0.73
    Activations Density 0.830%

    No Known Activations