© 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. 15500
    Prev
    Next
    INDEX
    Explanations

    mentions of military or combat-related terms

    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
    316
    +0.13
    0.6%
    442
    +0.12
    0.5%
    247
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.01
    103
    +0.12
    0.01
    202
    +0.10
    0.01
    Negative Logits
    creen
    -1.11
    çĦ
    -0.83
    mberg
    -0.80
    mates
    -0.77
    krit
    -0.72
     Ribbon
    -0.70
    mate
    -0.69
    wald
    -0.68
    ãģ®éŃĶ
    -0.67
    DN
    -0.67
    POSITIVE LOGITS
    ressive
    1.36
    ulse
    1.36
    ossible
    1.29
    ression
    1.26
    ractical
    1.17
    ossibility
    1.15
    ossibly
    1.14
    acts
    1.13
    unity
    1.10
    romptu
    1.09
    Activations Density 0.015%

    No Known Activations