© 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
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 10994
    Prev
    Next
    INDEX
    Explanations

    JavaScript related terms or concepts

    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
    326
    +0.11
    0.5%
    743
    +0.11
    0.5%
    188
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.01
    743
    +0.11
    0.01
    188
    +0.10
    0.01
    Negative Logits
    naires
    -0.86
    lain
    -0.86
    llah
    -0.79
    liest
    -0.75
    ŃĶ
    -0.74
    vol
    -0.69
     Sinclair
    -0.67
    ships
    -0.67
    rower
    -0.66
    ablishment
    -0.66
    POSITIVE LOGITS
    uration
    0.90
    DOM
    0.82
     interpreter
    0.81
     Bind
    0.80
    avascript
    0.80
    JS
    0.79
     JavaScript
    0.79
    Script
    0.77
    Works
    0.75
     Enabled
    0.75
    Activations Density 0.015%

    No Known Activations