© 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. 3347
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Barry."

    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
    642
    +0.13
    0.6%
    35
    +0.12
    0.5%
    269
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.13
    0.01
    326
    +0.12
    0.01
    364
    +0.10
    0.01
    Negative Logits
     Cosponsors
    -0.85
    PLA
    -0.82
    mble
    -0.80
    tnc
    -0.78
    */(
    -0.78
    achusetts
    -0.77
    eteria
    -0.77
    dfx
    -0.75
    phis
    -0.75
    hedral
    -0.74
    POSITIVE LOGITS
     Bonds
    1.12
     Lyndon
    0.99
    more
    0.95
     Armstrong
    0.94
     Allen
    0.93
     Kaufman
    0.85
     Sz
    0.80
    kus
    0.80
     Jennings
    0.77
     Seal
    0.77
    Activations Density 0.015%

    No Known Activations