© 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. 3150
    Prev
    Next
    INDEX
    Explanations

    detailed information about individuals and events related to politics and sports

    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
    +0.12
    0.6%
    705
    +0.10
    0.5%
    408
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    715
    +0.12
    0.03
    446
    +0.10
    0.03
    641
    +0.09
    0.03
    Negative Logits
    ById
    -0.68
    iots
    -0.63
    profit
    -0.62
    hod
    -0.61
    uxe
    -0.59
     Emails
    -0.59
    profits
    -0.59
    ts
    -0.58
    yon
    -0.58
    dos
    -0.58
    POSITIVE LOGITS
    tains
    0.77
     regards
    0.73
     regard
    0.72
     compared
    0.70
     associ
    0.67
     metic
    0.66
     considering
    0.65
     relates
    0.65
     confronts
    0.59
     dealing
    0.59
    Activations Density 0.135%

    No Known Activations