© 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 24576
    9. 8-RES_FS24576-JB
    11. 7914
    Prev
    Next
    INDEX
    Explanations

    numerical metrics or quantities in a structured format

    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
    314
    +0.12
    0.6%
    613
    +0.12
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    613
    +0.12
    0.02
    406
    +0.12
    0.02
    232
    +0.10
    0.02
    Negative Logits
     Archdemon
    -0.65
     innocence
    -0.59
     sunset
    -0.59
     WARN
    -0.58
    romeda
    -0.56
     amber
    -0.56
     condem
    -0.56
     reviewer
    -0.55
     appraisal
    -0.55
     mortar
    -0.55
    POSITIVE LOGITS
    lycer
    0.85
    bish
    0.83
    portation
    0.81
    idad
    0.74
    quist
    0.73
    ħĭ
    0.72
    tal
    0.71
    itte
    0.69
    edes
    0.69
    oxide
    0.69
    Activations Density 0.044%

    No Known Activations