© 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. 3799
    Prev
    Next
    INDEX
    Explanations

    the word "to"

    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
    709
    +0.13
    0.6%
    314
    +0.13
    0.6%
    373
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.13
    0.03
    519
    +0.13
    0.03
    462
    +0.12
    0.02
    Negative Logits
     unsu
    -0.57
     signs
    -0.57
     warrants
    -0.57
     redes
    -0.56
     coats
    -0.56
     banners
    -0.55
     displays
    -0.55
     prosecutions
    -0.54
     bundles
    -0.54
     signatures
    -0.54
    POSITIVE LOGITS
    ilet
    1.20
    pping
    1.19
    pped
    1.09
    othy
    0.93
    ffee
    0.92
    -$
    0.90
    plane
    0.90
    ast
    0.88
    ppers
    0.86
    pper
    0.84
    Activations Density 0.026%

    No Known Activations