© 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. 3840
    Prev
    Next
    INDEX
    Explanations

    locations and entities related to a legal case or medical treatment

    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
    314
    +0.11
    0.5%
    565
    +0.10
    0.4%
    86
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.11
    0.04
    375
    +0.10
    0.03
    492
    +0.09
    0.03
    Negative Logits
     IMAGES
    -0.79
     REUTERS
    -0.68
     Recent
    -0.66
     Shutterstock
    -0.66
     Actions
    -0.62
    cients
    -0.59
     Recession
    -0.59
     Activities
    -0.58
     recent
    -0.57
    zza
    -0.57
    POSITIVE LOGITS
     whence
    1.23
     thence
    1.09
    where
    1.02
     where
    1.01
     onward
    0.91
     onwards
    0.77
    SPONSORED
    0.74
     eventually
    0.72
    livion
    0.69
     then
    0.67
    Activations Density 0.368%

    No Known Activations