© 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. 14988
    Prev
    Next
    INDEX
    Explanations

    mentions of editorial content or opinions

    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
    679
    +0.12
    0.5%
    741
    +0.10
    0.5%
    7
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    741
    +0.12
    0.02
    508
    +0.10
    0.02
    399
    +0.10
    0.02
    Negative Logits
    bley
    -0.83
    enegger
    -0.75
    ilitary
    -0.73
    pered
    -0.69
    rises
    -0.67
    achi
    -0.63
    00200000
    -0.63
    eneg
    -0.62
    bands
    -0.62
    ulus
    -0.62
    POSITIVE LOGITS
    ials
    1.38
    ially
    1.25
    editor
    0.86
    iate
    0.84
    ial
    0.82
    rors
    0.81
    ror
    0.77
    hip
    0.75
    itatively
    0.75
    furt
    0.73
    Activations Density 0.018%

    No Known Activations