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 49152
    5. 8-RES_FS49152-JB
    6. 41228
    Prev
    Next
    INDEX
    Explanations

    numbers and numerical data related to statistics or quantities

    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
    341
    +0.09
    0.4%
    758
    +0.09
    0.4%
    219
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    384
    +0.09
    0.01
    758
    +0.09
    0.01
    1
    +0.09
    0.01
    Negative Logits
    owship
    -0.76
    rium
    -0.71
    yond
    -0.71
    ledged
    -0.69
    uve
    -0.69
    oglu
    -0.66
    anism
    -0.64
    oping
    -0.64
    anu
    -0.63
    lier
    -0.61
    POSITIVE LOGITS
     Photos
    0.99
     Expand
    0.84
     Advertisement
    0.80
     certs
    0.75
     ·
    0.71
     <!--
    0.70
     Image
    0.70
     msec
    0.69
     guiIcon
    0.69
     guiActiveUn
    0.68
    Activations Density 0.013%

    No Known Activations