© 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. 13850
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific event or brand name

    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
    216
    +0.16
    0.7%
    420
    +0.12
    0.6%
    726
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.16
    0.02
    406
    +0.12
    0.01
    326
    +0.11
    0.01
    Negative Logits
    s
    -0.84
    owship
    -0.81
    ity
    -0.81
    ials
    -0.79
    aciously
    -0.73
    itability
    -0.70
    antha
    -0.69
    lishes
    -0.69
    dies
    -0.68
    edly
    -0.67
    POSITIVE LOGITS
    chn
    1.16
    zzi
    1.05
    onga
    0.97
    chnology
    0.85
    anu
    0.84
    ague
    0.81
    ptic
    0.80
    tsky
    0.78
    eca
    0.77
    cki
    0.77
    Activations Density 0.046%

    No Known Activations