© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 20980
    Prev
    Next
    INDEX
    Explanations

    character names from a text

    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
    447
    +0.29
    1.4%
    543
    +0.11
    0.5%
    55
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.29
    0.07
    232
    +0.11
    0.07
    430
    +0.11
    0.07
    Negative Logits
    taboola
    -0.86
    tml
    -0.85
    dayName
    -0.82
    iminary
    -0.80
     td
    -0.77
    Ħ¢
    -0.76
    bidden
    -0.75
    ickr
    -0.74
    ledged
    -0.71
    quartered
    -0.70
    POSITIVE LOGITS
     Cage
    0.94
     Ryder
    0.91
     Kardashian
    0.91
     Hansen
    0.89
     Hardy
    0.88
     Robbins
    0.88
     Carter
    0.86
     Reeves
    0.86
     Cosby
    0.85
     Jenner
    0.84
    Activations Density 0.284%

    No Known Activations