© 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. 9326
    Prev
    Next
    INDEX
    Explanations

    verbs related to creating, doing, providing, complaining, deriving, writing, going, making, respecting, getting, playing, and coming

    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
    644
    +0.10
    0.5%
    143
    +0.10
    0.5%
    715
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.10
    0.08
    715
    +0.10
    0.06
    665
    +0.10
    0.07
    Negative Logits
    Applic
    -0.64
    fts
    -0.62
     Published
    -0.60
     Sample
    -0.60
    FIR
    -0.59
    pload
    -0.59
    lection
    -0.58
    adh
    -0.57
    pour
    -0.57
    Aid
    -0.56
    POSITIVE LOGITS
    ometimes
    0.78
    é¾
    0.68
     alot
    0.68
     ourselves
    0.67
    omorph
    0.66
     regularly
    0.65
     instinctively
    0.65
    ELY
    0.64
    ided
    0.61
     daily
    0.61
    Activations Density 0.521%

    No Known Activations