© 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. 8113
    Prev
    Next
    INDEX
    Explanations

    words related to survival

    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
    288
    +0.13
    0.6%
    575
    +0.11
    0.5%
    116
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.13
    0.02
    288
    +0.11
    0.01
    116
    +0.11
    0.01
    Negative Logits
    quart
    -0.75
    puter
    -0.74
    kson
    -0.70
    entious
    -0.69
     Anthem
    -0.67
    eneg
    -0.66
    endo
    -0.66
    estic
    -0.64
    umin
    -0.64
    FG
    -0.64
    POSITIVE LOGITS
     instincts
    1.02
    ously
    0.98
     survival
    0.89
    arily
    0.89
     instinct
    0.88
     Survive
    0.79
    ist
    0.76
    ists
    0.75
     Survival
    0.72
     deterrent
    0.71
    Activations Density 0.023%

    No Known Activations