© 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. 13538
    Prev
    Next
    INDEX
    Explanations

    phrases related to political happenings and office elections

    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
    480
    +0.42
    2.1%
    447
    +0.14
    0.7%
    303
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.42
    -0.00
    119
    +0.14
    0.04
    266
    +0.09
    0.08
    Negative Logits
     respectively
    -0.62
    ãĤ´ãĥ³
    -0.58
    iga
    -0.54
    interstitial
    -0.52
    inducing
    -0.51
    FAULT
    -0.50
     ("
    -0.49
    bia
    -0.48
    their
    -0.47
     Prix
    -0.47
    POSITIVE LOGITS
     ..."
    1.14
    [/
    1.06
    %"
    1.05
     âĢ¦"
    0.99
    )",
    0.98
    ,''
    0.97
     [
    0.96
    ?'
    0.94
    )"
    0.92
    ),"
    0.89
    Activations Density 0.985%

    No Known Activations