© 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. 3329
    Prev
    Next
    INDEX
    Explanations

    words related to partnerships and collaborations

    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
    718
    +0.14
    0.7%
    508
    +0.14
    0.6%
    608
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.14
    0.06
    508
    +0.14
    0.06
    665
    +0.13
    0.06
    Negative Logits
    quickShipAvailable
    -0.81
    answered
    -0.71
    aturday
    -0.66
    CI
    -0.66
    abiding
    -0.66
    thing
    -0.66
    erence
    -0.64
    Talking
    -0.64
    isSpecialOrderable
    -0.64
    living
    -0.62
    POSITIVE LOGITS
     ensure
    1.33
     create
    1.32
     provide
    1.24
     deliver
    1.21
     produce
    1.18
     maximize
    1.17
     develop
    1.16
     determine
    1.15
     promote
    1.15
     formulate
    1.13
    Activations Density 0.143%

    No Known Activations