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. 1175
    Prev
    Next
    INDEX
    Explanations

    direct quotes and citations in text

    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
    178
    +0.11
    0.5%
    447
    +0.11
    0.5%
    386
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.11
    0.03
    255
    +0.11
    0.02
    45
    +0.11
    0.02
    Negative Logits
    iaries
    -0.69
    ĻĤ
    -0.69
    kw
    -0.68
    eka
    -0.67
    cephal
    -0.66
     prenatal
    -0.62
    mit
    -0.62
     Kut
    -0.62
    Shot
    -0.62
    holder
    -0.61
    POSITIVE LOGITS
     ie
    0.71
    izu
    0.68
    /"
    0.65
    £
    0.63
    ushima
    0.63
    [
    0.62
    VID
    0.60
    ''.
    0.59
     (£
    0.59
     Mao
    0.59
    Activations Density 0.039%

    No Known Activations