© 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. 14324
    Prev
    Next
    INDEX
    Explanations

    information related to electoral results

    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
    661
    +0.11
    0.5%
    366
    +0.11
    0.5%
    68
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    607
    +0.11
    0.04
    556
    +0.11
    0.03
    366
    +0.11
    0.03
    Negative Logits
    someone
    -0.77
    SourceFile
    -0.71
    culosis
    -0.67
    zsche
    -0.65
    ļéĨĴ
    -0.65
    kernel
    -0.65
    mud
    -0.62
    gone
    -0.61
    Phys
    -0.61
    á½
    -0.59
    POSITIVE LOGITS
     respectively
    2.02
     alike
    1.31
     respective
    1.04
     halves
    1.00
     selves
    0.99
     editions
    0.96
     versions
    0.95
     eras
    0.92
     grades
    0.91
    eele
    0.89
    Activations Density 0.147%

    No Known Activations