© 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. 2997
    Prev
    Next
    INDEX
    Explanations

    parentheses

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    314
    +0.18
    0.9%
    160
    +0.18
    0.8%
    640
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.18
    0.04
    314
    +0.18
    0.01
    627
    +0.14
    0.03
    Negative Logits
     buoy
    -0.83
     orn
    -0.72
     Prism
    -0.72
     lav
    -0.72
     dense
    -0.71
     reasonably
    -0.69
     creep
    -0.69
     irresist
    -0.68
     Leilan
    -0.67
     prone
    -0.66
    POSITIVE LOGITS
    sic
    1.82
    laughs
    1.66
    Laughs
    1.35
    âĢ¦)
    1.34
    emphasis
    1.31
    ...)
    1.30
    insert
    1.17
    laughter
    1.16
    laugh
    1.15
    Wednesday
    1.10
    Activations Density 0.058%

    No Known Activations