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. 23627
    Prev
    Next
    INDEX
    Explanations

    measurements and units of measurement related to physical quantities

    oai_token-act-pair · gpt-4o-miniTriggered 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
    23
    +0.11
    0.5%
    67
    +0.10
    0.4%
    95
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    545
    +0.11
    0.03
    23
    +0.10
    0.03
    67
    +0.10
    0.03
    Negative Logits
    bidden
    -0.82
    furt
    -0.72
    naissance
    -0.68
    mentioned
    -0.65
    eer
    -0.63
     Valentine
    -0.58
    inburgh
    -0.58
     feast
    -0.58
    grade
    -0.57
    angered
    -0.57
    POSITIVE LOGITS
    icka
    0.95
     diameter
    0.91
     increments
    0.83
    pi
    0.83
    Pa
    0.82
    ²
    0.82
    ·
    0.80
    .;
    0.79
    ./
    0.77
    pees
    0.77
    Activations Density 0.050%

    No Known Activations