© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1196
    Prev
    Next
    INDEX
    Explanations

    words related to crises and emergencies

    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
    288
    +0.17
    0.8%
    447
    +0.15
    0.7%
    52
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.03
    132
    +0.15
    0.03
    651
    +0.11
    0.03
    Negative Logits
    alty
    -0.89
    rosse
    -0.81
    alties
    -0.80
    ipedia
    -0.79
    Īè
    -0.77
    icrobial
    -0.77
    eston
    -0.76
    ells
    -0.76
    eele
    -0.75
    GC
    -0.73
    POSITIVE LOGITS
     plag
    1.05
     crisis
    1.01
     aver
    1.01
     engulf
    1.01
     epidemic
    0.93
     crises
    0.89
     unfolding
    0.88
     gripping
    0.85
     outbreak
    0.84
     involving
    0.82
    Activations Density 0.080%

    No Known Activations