© 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. 10989
    Prev
    Next
    INDEX
    Explanations

    references to the historical event of Pearl Harbor

    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
    526
    +0.12
    0.6%
    571
    +0.10
    0.5%
    484
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.01
    288
    +0.10
    0.01
    699
    +0.10
    0.01
    Negative Logits
    NRS
    -0.72
    arios
    -0.69
    SPONSORED
    -0.68
    enegger
    -0.66
    hered
    -0.65
    dit
    -0.65
    ellar
    -0.63
     steroid
    -0.63
    olved
    -0.62
    PDATE
    -0.61
    POSITIVE LOGITS
     Harbor
    1.18
    stein
    0.93
     Harbour
    0.90
    ãĥĥãĥī
    0.86
     Pearl
    0.84
    ls
    0.78
    Pear
    0.77
    sburg
    0.75
     Ear
    0.75
    ridge
    0.73
    Activations Density 0.027%

    No Known Activations