© 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. 6165
    Prev
    Next
    INDEX
    Explanations

    This neuron detects the word "nanosecond" and variations like "ose" when it appears in scientific or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @trainjumperx

    words related to medical conditions specifically related to the nose

    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
    +0.13
    0.6%
    99
    +0.12
    0.5%
    661
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.13
    0.01
    579
    +0.12
    0.01
    59
    +0.10
    0.01
    Negative Logits
    icum
    -0.78
    agne
    -0.74
    osterone
    -0.72
    azon
    -0.72
    oola
    -0.71
    ersen
    -0.71
    rators
    -0.69
    apolis
    -0.68
    arios
    -0.67
    rade
    -0.66
    POSITIVE LOGITS
    idon
    1.16
    cond
    1.14
    velt
    1.13
    lect
    1.13
    eker
    0.96
    ph
    0.92
    lihood
    0.92
    lli
    0.90
    gger
    0.90
    LECT
    0.90
    Activations Density 0.022%

    No Known Activations