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. 26496
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and"

    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
    430
    +0.13
    0.6%
    516
    +0.10
    0.5%
    543
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    543
    +0.13
    0.03
    659
    +0.10
    0.03
    363
    +0.10
    0.02
    Negative Logits
    artifacts
    -0.79
    wcs
    -0.78
    minist
    -0.76
    mining
    -0.73
    aneously
    -0.72
    ombo
    -0.71
    different
    -0.70
    ital
    -0.70
    ibaba
    -0.70
    trop
    -0.70
    POSITIVE LOGITS
     Sons
    1.01
     Associates
    0.95
     Sharon
    0.90
     Kyl
    0.88
     Jerry
    0.87
     Michelle
    0.87
     Mary
    0.87
     Morty
    0.87
     Tammy
    0.86
     Tanner
    0.86
    Activations Density 0.048%

    No Known Activations