© 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. 6543
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Mu" followed by various letters, possibly focusing on a specific individual or topic

    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
    569
    +0.12
    0.5%
    628
    +0.10
    0.5%
    278
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    278
    +0.12
    0.01
    628
    +0.10
    0.01
    659
    +0.10
    0.01
    Negative Logits
    é¾įå
    -0.75
     UID
    -0.68
     Ajax
    -0.67
     Jonah
    -0.66
     Nept
    -0.64
     SPACE
    -0.63
     Dracula
    -0.63
    姫
    -0.63
     Drift
    -0.62
     Eleven
    -0.61
    POSITIVE LOGITS
    lder
    1.36
    hammad
    1.20
    ahah
    1.11
    gee
    1.03
    selage
    1.03
    zik
    1.02
    pload
    1.00
    ñ
    0.99
    ld
    0.99
    udge
    0.99
    Activations Density 0.009%

    No Known Activations