© 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 49152
    9. 8-RES_FS49152-JB
    11. 41502
    Prev
    Next
    INDEX
    Explanations

    words related to individuals or entities on the run from the law or evading capture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    +0.17
    0.8%
    685
    +0.11
    0.5%
    453
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.01
    453
    +0.11
    0.01
    727
    +0.10
    0.01
    Negative Logits
    sembly
    -0.93
     Seym
    -0.88
    istry
    -0.86
    ensing
    -0.83
    ovember
    -0.82
    imore
    -0.81
    ayers
    -0.77
    bourg
    -0.77
    merce
    -0.76
    anguage
    -0.75
    POSITIVE LOGITS
     slaves
    0.81
     runaway
    0.81
    draft
    0.72
     pregnancy
    0.67
     predators
    0.66
     cabbage
    0.66
     slave
    0.65
     pregnancies
    0.64
     Kenyan
    0.64
     oats
    0.63
    Activations Density 0.009%

    No Known Activations