© 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. 19601
    Prev
    Next
    INDEX
    Explanations

    words related to safety precautions, security measures, and best practices

    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
    542
    +0.12
    0.5%
    705
    +0.11
    0.5%
    447
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    705
    +0.12
    0.04
    542
    +0.11
    0.04
    50
    +0.10
    0.04
    Negative Logits
    ĸļ
    -0.72
    noxious
    -0.72
    gian
    -0.70
    NetMessage
    -0.68
    ancies
    -0.68
    qus
    -0.62
    ighters
    -0.61
    ammy
    -0.60
    ymes
    -0.59
    zzy
    -0.59
    POSITIVE LOGITS
     imaginable
    0.92
     available
    0.89
     option
    0.78
     for
    0.74
    Alternative
    0.73
     conceivable
    0.72
     approach
    0.72
     possible
    0.68
    escape
    0.68
     practicable
    0.67
    Activations Density 0.143%

    No Known Activations