© 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. 22643
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Solomon" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    444
    +0.10
    0.5%
    99
    +0.10
    0.5%
    421
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.03
    444
    +0.10
    0.02
    659
    +0.10
    0.02
    Negative Logits
    haw
    -0.79
    ansas
    -0.73
    hire
    -0.72
    ees
    -0.70
    giving
    -0.69
    RF
    -0.68
    DN
    -0.68
    href
    -0.68
    chell
    -0.67
    rence
    -0.66
    POSITIVE LOGITS
    osal
    0.84
    ufact
    0.83
    pei
    0.79
    afort
    0.77
    stros
    0.75
    merce
    0.73
    opsis
    0.73
    chio
    0.72
    ography
    0.71
    pson
    0.71
    Activations Density 0.077%

    No Known Activations