© 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. 3681
    Prev
    Next
    INDEX
    Explanations

    references to updates or changes being made by a company

    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
    393
    +0.10
    0.5%
    362
    +0.10
    0.4%
    670
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.07
    608
    +0.10
    0.06
    670
    +0.10
    0.05
    Negative Logits
    hari
    -0.95
    orgetown
    -0.82
    lehem
    -0.81
    nin
    -0.81
    tale
    -0.80
    iece
    -0.80
    olkien
    -0.78
    omsky
    -0.78
    Filename
    -0.77
    mire
    -0.76
    POSITIVE LOGITS
     own
    1.53
     proprietary
    1.23
     products
    1.21
     customers
    1.21
     flagship
    1.19
     competitors
    1.19
     subsidiaries
    1.09
     employees
    1.08
     respective
    1.06
     patented
    1.06
    Activations Density 0.213%

    No Known Activations