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. 2658
    Prev
    Next
    INDEX
    Explanations

    news sources and content related to legal matters or specific significant events

    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
    549
    +0.12
    0.5%
    332
    +0.10
    0.5%
    668
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.12
    0.04
    455
    +0.10
    0.05
    506
    +0.10
    0.04
    Negative Logits
    aeper
    -0.85
    achine
    -0.72
    Ħ¢
    -0.71
    eg
    -0.70
    eer
    -0.68
    tarians
    -0.66
    jriwal
    -0.65
    PDATE
    -0.63
    wagen
    -0.63
    ecause
    -0.62
    POSITIVE LOGITS
    Fed
    1.02
    books
    0.94
    book
    0.85
    finding
    0.82
    forge
    0.82
     whence
    0.81
    Forge
    0.78
    finder
    0.77
     Sources
    0.77
     thereof
    0.76
    Activations Density 0.634%

    No Known Activations