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 3072
    5. 8-RES_FS3072-JB
    6. 518
    Prev
    Next
    INDEX
    Explanations

    time-related words and activities happening during the night

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    178
    +0.12
    0.5%
    152
    +0.10
    0.4%
    158
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.12
    0.06
    178
    +0.10
    0.06
    158
    +0.09
    0.05
    Negative Logits
    achev
    -0.81
    bard
    -0.78
    xon
    -0.76
     Canaver
    -0.70
    ignty
    -0.69
    cules
    -0.69
    emort
    -0.67
    00000000
    -0.67
    dinand
    -0.67
    ortium
    -0.67
    POSITIVE LOGITS
    cap
    0.86
    mares
    0.78
    mar
    0.76
    fall
    0.76
     sky
    0.75
    life
    0.74
    night
    0.74
     nights
    0.74
     ow
    0.72
     commute
    0.72
    Activations Density 0.454%

    No Known Activations