© 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. 3838
    Prev
    Next
    INDEX
    Explanations

    terms related to health, medical conditions, and medical treatments

    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
    480
    +0.34
    1.6%
    130
    +0.09
    0.4%
    90
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.34
    0.06
    130
    +0.09
    0.04
    537
    +0.09
    0.06
    Negative Logits
     .)
    -0.67
    ãĤ¨ãĥ«
    -0.55
    .):
    -0.54
    é¾įåĸļ士
    -0.53
    ģĸ
    -0.52
     Canaver
    -0.51
     awoken
    -0.51
     distinctly
    -0.50
    ccording
    -0.49
    WARD
    -0.49
    POSITIVE LOGITS
     etc
    0.91
    ®,
    0.62
    !,
    0.58
    +,
    0.58
    ,[
    0.57
    *,
    0.54
    ?,
    0.54
    ,
    0.54
     thereof
    0.54
     and
    0.53
    Activations Density 0.693%

    No Known Activations