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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1374
    Prev
    Next
    INDEX
    Explanations

    names related to individuals or characters

    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
    16
    +0.12
    0.5%
    147
    +0.11
    0.5%
    71
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    147
    +0.12
    0.01
    16
    +0.11
    0.01
    343
    +0.11
    0.01
    Negative Logits
    issance
    -0.82
     Indust
    -0.65
     accommodation
    -0.63
    llah
    -0.63
    coe
    -0.62
    ritional
    -0.62
    herty
    -0.61
     Sparkle
    -0.61
    Ire
    -0.61
    rial
    -0.61
    POSITIVE LOGITS
    joy
    1.00
    ings
    0.98
    mails
    0.95
    ingly
    0.92
    adelphia
    0.91
    switch
    0.85
    uminati
    0.85
    req
    0.84
    mong
    0.81
    killer
    0.80
    Activations Density 0.024%

    No Known Activations