© 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. 3300
    Prev
    Next
    INDEX
    Explanations

    verbs associated with causing effects or changes

    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
    643
    +0.11
    0.5%
    41
    +0.11
    0.5%
    298
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    664
    +0.11
    0.03
    298
    +0.11
    0.03
    665
    +0.10
    0.03
    Negative Logits
    ãĥĨ
    -0.76
    ãĥ¬
    -0.65
    æ©Ł
    -0.65
     Kend
    -0.63
    ãĥ¼ãĥĨãĤ£
    -0.63
    å°Ĩ
    -0.62
    anamo
    -0.62
    PHOTOS
    -0.62
    ãĥIJ
    -0.62
    acies
    -0.60
    POSITIVE LOGITS
     comfortably
    0.89
     worthwhile
    0.83
     reliably
    0.78
     oneself
    0.76
     anymore
    0.73
    paren
    0.72
     warrants
    0.70
     warrant
    0.69
     safely
    0.69
    itant
    0.68
    Activations Density 0.187%

    No Known Activations