© 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. 15107
    Prev
    Next
    INDEX
    Explanations

    dates spanning several years

    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
    373
    +0.73
    6.5%
    756
    +0.16
    1.4%
    218
    +0.09
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.73
    -0.09
    756
    +0.16
    -0.05
    326
    +0.09
    0.15
    Negative Logits
    bryce
    -0.42
    ".[
    -0.35
    ).[
    -0.33
    withstanding
    -0.31
    ."[
    -0.31
    æѦ
    -0.29
     Sunni
    -0.29
    Äģ
    -0.29
    iak
    -0.29
    osate
    -0.28
    POSITIVE LOGITS
    anity
    0.32
     showc
    0.28
     typo
    0.27
    renheit
    0.27
     fades
    0.27
     err
    0.27
     fade
    0.26
    epad
    0.26
    cedes
    0.25
    pmwiki
    0.25
    Activations Density 3.776%

    No Known Activations