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. 19240
    Prev
    Next
    INDEX
    Explanations

    names of cities and places

    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
    41
    +0.12
    0.5%
    105
    +0.10
    0.5%
    579
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.05
    232
    +0.10
    0.05
    41
    +0.10
    0.04
    Negative Logits
    kefeller
    -0.77
    ufact
    -0.68
    âĸ¬
    -0.68
     illeg
    -0.67
    cess
    -0.66
    theless
    -0.65
    ificial
    -0.64
     Argent
    -0.62
    plane
    -0.61
     Qiao
    -0.61
    POSITIVE LOGITS
    atsu
    0.91
    nen
    0.91
    uku
    0.91
    ikuman
    0.86
    uchi
    0.85
    hai
    0.81
    ovi
    0.78
    aki
    0.77
    otos
    0.77
    ui
    0.76
    Activations Density 0.129%

    No Known Activations