© 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. 308
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "El Nino"

    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
    267
    +0.12
    0.5%
    756
    +0.11
    0.5%
    248
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.02
    343
    +0.11
    0.02
    406
    +0.11
    0.02
    Negative Logits
    nesday
    -0.94
    lished
    -0.84
    ecause
    -0.74
     Asgard
    -0.73
    matically
    -0.71
    enance
    -0.70
    adr
    -0.69
    rahim
    -0.69
    chool
    -0.68
    anked
    -0.67
    POSITIVE LOGITS
    etti
    0.91
    phrine
    0.88
    ero
    0.88
    eland
    0.87
    lli
    0.86
    opsis
    0.84
    xit
    0.78
     Rossi
    0.76
    lla
    0.76
    zzi
    0.76
    Activations Density 0.104%

    No Known Activations