© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 10623
    Prev
    Next
    INDEX
    Explanations

    numerical values within brackets

    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
    314
    +0.13
    0.6%
    404
    +0.10
    0.5%
    632
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    114
    +0.13
    0.04
    632
    +0.10
    0.03
    278
    +0.10
    0.03
    Negative Logits
    Desktop
    -0.56
    (&
    -0.53
     artif
    -0.53
     Telegram
    -0.52
     Meter
    -0.52
    Ͻ
    -0.52
     iTunes
    -0.52
     mush
    -0.51
    ãĥĦ
    -0.50
     administrator
    -0.50
    POSITIVE LOGITS
    ãĥİ
    0.71
    *.
    0.70
    arcer
    0.69
    and
    0.66
     versus
    0.62
     and
    0.61
    without
    0.61
    theless
    0.61
    selves
    0.60
    +.
    0.60
    Activations Density 0.131%

    No Known Activations