Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 21614
    Prev
    Next
    INDEX
    Explanations

    words related to fire and flames

    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
    +0.12
    0.5%
    331
    +0.11
    0.5%
    726
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.02
    288
    +0.11
    0.03
    331
    +0.10
    0.02
    Negative Logits
    alian
    -0.82
    oral
    -0.73
    laus
    -0.72
    istan
    -0.71
    ortment
    -0.70
    llah
    -0.68
    ournal
    -0.68
    los
    -0.67
    ographics
    -0.67
    sum
    -0.67
    POSITIVE LOGITS
     flame
    1.12
     flames
    1.05
     hotter
    0.99
    flies
    0.97
     candles
    0.97
     candle
    0.95
     extinguished
    0.94
    flame
    0.93
     blaze
    0.93
     ashes
    0.92
    Activations Density 0.048%

    No Known Activations