© 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 49152
    9. 8-RES_FS49152-JB
    11. 25985
    Prev
    Next
    INDEX
    Explanations

    references to different forms of the word "si."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    235
    +0.11
    0.5%
    373
    +0.11
    0.5%
    289
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.01
    343
    +0.11
    0.01
    502
    +0.10
    0.01
    Negative Logits
    ttes
    -0.83
    worthiness
    -0.82
    ICA
    -0.71
    worn
    -0.67
    side
    -0.66
    landish
    -0.66
    lain
    -0.65
    rals
    -0.63
     EVs
    -0.63
    tails
    -0.63
    POSITIVE LOGITS
    pling
    1.21
    ples
    1.02
    plings
    0.97
    pler
    0.90
    plin
    0.82
    enza
    0.82
    iple
    0.82
    ylum
    0.78
    plane
    0.77
    ption
    0.77
    Activations Density 0.005%

    No Known Activations