© 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. 7432
    Prev
    Next
    INDEX
    Explanations

    the word "ate" in various verb forms

    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
    59
    +0.14
    0.7%
    366
    +0.10
    0.5%
    99
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.14
    0.02
    99
    +0.10
    0.02
    404
    +0.10
    0.02
    Negative Logits
    ness
    -0.76
    enegger
    -0.75
    nesses
    -0.73
    NESS
    -0.73
    ingen
    -0.71
    endon
    -0.71
    dale
    -0.70
    sung
    -0.68
    uggest
    -0.68
    stru
    -0.67
    POSITIVE LOGITS
    chnology
    1.18
    rers
    1.04
    llular
    1.00
    rer
    0.82
    lli
    0.82
    anu
    0.80
    lled
    0.80
    xus
    0.75
    ctic
    0.72
    vich
    0.71
    Activations Density 0.080%

    No Known Activations