© 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 EvalsExportsinterp-engineNEWAPI 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. 5746
    Prev
    Next
    INDEX
    Explanations

    keywords related to the company "Embarkero Technologies" and the job change to the position of "Product Manager."

    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
    373
    +0.14
    0.6%
    588
    +0.12
    0.6%
    31
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    588
    +0.14
    0.01
    701
    +0.12
    0.01
    373
    +0.11
    -0.00
    Negative Logits
    mble
    -0.70
    lves
    -0.65
    lihood
    -0.62
    fulness
    -0.61
    hran
    -0.60
    LOAD
    -0.60
    LV
    -0.59
    DAQ
    -0.59
    bowl
    -0.59
    glers
    -0.59
    POSITIVE LOGITS
    otics
    1.01
    inia
    0.92
    issa
    0.89
    itizen
    0.85
    aine
    0.82
    inating
    0.80
    illo
    0.79
    inelli
    0.78
    adia
    0.78
    iso
    0.77
    Activations Density 0.017%

    No Known Activations