© 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. 2982
    Prev
    Next
    INDEX
    Explanations

    text related to legal documents or official reports

    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
    393
    +0.22
    1.0%
    500
    +0.13
    0.6%
    447
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.22
    0.04
    393
    +0.13
    0.03
    362
    +0.12
    0.04
    Negative Logits
    rade
    -0.78
    gat
    -0.75
    abilities
    -0.75
    ovo
    -0.73
    hei
    -0.72
    unta
    -0.72
    zon
    -0.71
    strate
    -0.69
    placed
    -0.68
    opers
    -0.68
    POSITIVE LOGITS
     latest
    1.28
     entirety
    1.16
     entire
    1.15
     newest
    1.03
     full
    1.02
     rest
    1.02
     remainder
    0.99
     original
    0.98
     contents
    0.98
     slideshow
    0.95
    Activations Density 0.111%

    No Known Activations