© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1392
    Prev
    Next
    INDEX
    Explanations

    words related to government, policies, and regulations

    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
    481
    +0.13
    0.6%
    393
    +0.11
    0.5%
    655
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    655
    +0.13
    0.06
    203
    +0.11
    0.06
    713
    +0.10
    0.05
    Negative Logits
    ses
    -0.74
    case
    -0.73
    uta
    -0.73
    acas
    -0.71
    iots
    -0.69
    umbn
    -0.69
    atan
    -0.68
    anz
    -0.68
    zip
    -0.67
    inar
    -0.67
    POSITIVE LOGITS
     consequently
    1.36
     moreover
    1.35
     furthermore
    1.33
     therefore
    1.29
     rightfully
    1.24
     hence
    1.24
     thus
    1.16
     rightly
    1.13
     although
    1.09
     luckily
    1.03
    Activations Density 0.208%

    No Known Activations