© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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 12288
    9. 8-RES_FS12288-JB
    11. 1465
    Prev
    Next
    INDEX
    Explanations

    names of people and places related to a specific event or location

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    145
    +0.12
    0.5%
    353
    +0.10
    0.5%
    693
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.09
    579
    +0.10
    0.07
    232
    +0.10
    0.07
    Negative Logits
    ĸļ
    -0.88
    ipeg
    -0.85
    EStream
    -0.80
    behind
    -0.77
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.75
    cause
    -0.74
    sheet
    -0.73
    draft
    -0.73
    wt
    -0.72
    authorized
    -0.71
    POSITIVE LOGITS
     Parish
    1.09
     Palace
    0.96
     Syndrome
    0.90
     Islands
    0.87
    phia
    0.85
    opsis
    0.85
     Cove
    0.83
     Gardens
    0.83
     Royale
    0.82
    ère
    0.82
    Activations Density 0.513%

    No Known Activations