© 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. 3737
    Prev
    Next
    INDEX
    Explanations

    phrases related to community events and societal reactions

    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
    537
    +0.10
    0.5%
    248
    +0.10
    0.4%
    596
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    517
    +0.10
    0.03
    537
    +0.10
    0.03
    596
    +0.09
    0.03
    Negative Logits
    tein
    -0.75
    Ļ½
    -0.72
    paren
    -0.72
    omorphic
    -0.71
    stant
    -0.70
    ulic
    -0.67
    icular
    -0.67
    ãĥ¯ãĥ³
    -0.65
    vironment
    -0.64
    ackets
    -0.63
    POSITIVE LOGITS
    /"
    0.91
     revealing
    0.61
     Dickinson
    0.61
    sic
    0.60
     owing
    0.60
     because
    0.59
     adding
    0.59
     Alz
    0.58
    Reply
    0.57
     Wynne
    0.57
    Activations Density 0.077%

    No Known Activations