© 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. 2969
    Prev
    Next
    INDEX
    Explanations

    the word "pet" and related terms

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.13
    0.6%
    433
    +0.12
    0.5%
    456
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    433
    +0.13
    0.02
    456
    +0.12
    0.02
    457
    +0.10
    0.01
    Negative Logits
    xual
    -0.77
    éĹĺ
    -0.75
     PUBLIC
    -0.71
    IDER
    -0.69
     seeded
    -0.68
     doub
    -0.66
    DERR
    -0.65
     plotted
    -0.65
    UME
    -0.63
    ources
    -0.61
    POSITIVE LOGITS
    ertodd
    1.36
    rified
    1.15
    abyte
    1.14
    abytes
    1.09
    roleum
    1.07
    unia
    1.03
    pet
    1.03
    itions
    1.00
    rification
    0.99
    rol
    0.97
    Activations Density 0.022%

    No Known Activations