© 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. 7905
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Noah"

    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
    421
    +0.13
    0.6%
    377
    +0.11
    0.5%
    346
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.13
    0.01
    628
    +0.11
    0.01
    343
    +0.10
    0.01
    Negative Logits
    rosse
    -0.80
    staff
    -0.78
    arching
    -0.77
    pired
    -0.75
    netic
    -0.75
    lished
    -0.74
    leading
    -0.74
    ordinate
    -0.71
    notation
    -0.70
    etitive
    -0.69
    POSITIVE LOGITS
     Webster
    1.00
     Noah
    0.95
     Ark
    0.86
     Ness
    0.79
     Feldman
    0.77
    omin
    0.73
    ÃŃs
    0.71
     Christensen
    0.70
     Lenn
    0.69
    mberg
    0.69
    Activations Density 0.020%

    No Known Activations