© 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. 14771
    Prev
    Next
    INDEX
    Explanations

    sequences related to lists or bullet points

    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
    393
    +0.15
    0.7%
    409
    +0.11
    0.5%
    362
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.15
    0.02
    97
    +0.11
    0.02
    362
    +0.11
    0.03
    Negative Logits
    imeter
    -0.76
    ester
    -0.73
    jad
    -0.72
    uca
    -0.72
    matter
    -0.72
    umption
    -0.72
    iage
    -0.70
    ismo
    -0.70
    OOD
    -0.70
    imet
    -0.69
    POSITIVE LOGITS
     names
    1.03
     accomplishments
    0.99
     grievances
    0.98
     sorts
    0.97
     reasons
    0.93
     allowable
    0.90
     acron
    0.90
     items
    0.90
     celebrities
    0.89
     topics
    0.86
    Activations Density 0.099%

    No Known Activations