© 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. 8523
    Prev
    Next
    INDEX
    Explanations

    technical terms and details related to various topics

    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
    255
    +0.14
    0.7%
    132
    +0.11
    0.5%
    724
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.14
    0.03
    724
    +0.11
    0.03
    132
    +0.11
    0.03
    Negative Logits
    bern
    -0.80
    escription
    -0.79
    kson
    -0.73
    inav
    -0.73
    ergy
    -0.72
    kers
    -0.71
    GER
    -0.71
    iger
    -0.71
    acan
    -0.69
    kef
    -0.69
    POSITIVE LOGITS
     Peb
    0.99
     Principle
    0.84
     quot
    0.82
    ously
    0.74
     quo
    0.70
    fulness
    0.69
    uous
    0.69
    bringer
    0.69
     Pwr
    0.69
     charms
    0.68
    Activations Density 0.078%

    No Known Activations