© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14779
    Prev
    Next
    INDEX
    Explanations

    phrases related to political and international relations

    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
    +0.23
    1.1%
    447
    +0.15
    0.7%
    464
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    546
    +0.23
    0.06
    418
    +0.15
    0.06
    480
    +0.14
    0.02
    Negative Logits
    minster
    -0.68
    ãĥ¥
    -0.59
    oya
    -0.58
    apsed
    -0.57
    Thumbnail
    -0.57
    Override
    -0.55
    iku
    -0.55
    ener
    -0.54
    ãģ®
    -0.54
    ãĤĮ
    -0.54
    POSITIVE LOGITS
     including
    0.86
     namely
    0.86
     wherein
    0.81
     huh
    0.81
     please
    0.80
     preferably
    0.74
     respectively
    0.73
     comprising
    0.70
     culminating
    0.70
     albeit
    0.70
    Activations Density 0.270%

    No Known Activations