© 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. 22639
    Prev
    Next
    INDEX
    Explanations

    names of notable female figures

    oai_token-act-pair · gpt-4o-miniTriggered 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
    612
    +0.12
    0.5%
    430
    +0.11
    0.5%
    682
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    350
    +0.12
    0.03
    659
    +0.11
    0.03
    430
    +0.11
    0.03
    Negative Logits
    */(
    -0.81
    atory
    -0.78
    hire
    -0.76
    erate
    -0.73
    shit
    -0.72
    ondon
    -0.72
    atories
    -0.71
    raltar
    -0.71
    nation
    -0.69
    ool
    -0.69
    POSITIVE LOGITS
     DeVos
    1.10
     Mae
    1.07
     Marie
    1.07
     Lynn
    1.05
     Louise
    1.04
     herself
    0.99
     Anne
    0.99
     Jane
    0.99
     Patricia
    0.97
     Ellen
    0.94
    Activations Density 0.045%

    No Known Activations