© 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. 17312
    Prev
    Next
    INDEX
    Explanations

    phrases related to work and tasks

    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
    650
    +0.09
    0.4%
    235
    +0.09
    0.4%
    674
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.09
    0.05
    234
    +0.09
    0.04
    455
    +0.09
    0.04
    Negative Logits
    deen
    -0.72
    sburg
    -0.72
    waukee
    -0.71
    atcher
    -0.71
    bah
    -0.71
    here
    -0.70
    lass
    -0.69
    liga
    -0.69
    ramid
    -0.69
    pherd
    -0.69
    POSITIVE LOGITS
     caveats
    1.20
     regard
    1.08
     impunity
    1.05
     ease
    1.05
     exceptions
    1.02
     hindsight
    0.99
     haste
    0.96
     twists
    0.96
     emphasis
    0.94
     flair
    0.94
    Activations Density 0.186%

    No Known Activations