© 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. 3193
    Prev
    Next
    INDEX
    Explanations

    phrases related to political matters, especially opinions and stances related to international relations and policy decisions

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    113
    +0.12
    0.5%
    476
    +0.11
    0.5%
    21
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    476
    +0.12
    0.04
    506
    +0.11
    0.04
    313
    +0.10
    0.04
    Negative Logits
     Devi
    -0.75
     summons
    -0.68
    ammy
    -0.67
     Reincarn
    -0.67
     Incarnation
    -0.66
    illac
    -0.65
     LTD
    -0.65
     licences
    -0.65
    iasis
    -0.65
     TAMADRA
    -0.64
    POSITIVE LOGITS
     commentators
    1.01
     pundits
    0.97
     onlook
    0.94
     academia
    0.94
     pund
    0.93
     insiders
    0.92
    untled
    0.89
    odox
    0.86
     influential
    0.85
     commenters
    0.85
    Activations Density 0.409%

    No Known Activations