© 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. 16381
    Prev
    Next
    INDEX
    Explanations

    issues or topics of importance and controversy within a community or society

    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
    447
    +0.19
    0.9%
    481
    +0.14
    0.6%
    621
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.05
    737
    +0.14
    0.03
    225
    +0.13
    0.03
    Negative Logits
    rily
    -0.77
    uly
    -0.75
    ately
    -0.72
    viously
    -0.68
    aciously
    -0.68
     Carbuncle
    -0.67
    uled
    -0.65
    particularly
    -0.64
    reau
    -0.64
    cellaneous
    -0.63
    POSITIVE LOGITS
    wives
    0.71
    acea
    0.68
    DonaldTrump
    0.67
    ument
    0.67
    UID
    0.65
    worthiness
    0.64
    estate
    0.64
    ITNESS
    0.63
    ãĤ¬
    0.63
    ãĤ·ãĥ£
    0.63
    Activations Density 0.261%

    No Known Activations