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 768
    5. 8-RES_FS768-JB
    6. 493
    Prev
    Next
    INDEX
    Explanations

    examples of social issues and societal disparities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    157
    +0.11
    0.5%
    756
    +0.11
    0.5%
    420
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.18
    102
    +0.11
    0.21
    756
    +0.10
    -0.07
    Negative Logits
    FIN
    -0.71
    iversary
    -0.69
    atform
    -0.68
    eur
    -0.67
    icio
    -0.65
    DK
    -0.64
    onement
    -0.63
    inth
    -0.63
    ulus
    -0.62
    soType
    -0.62
    POSITIVE LOGITS
     themselves
    1.51
     prolifer
    1.18
     clustered
    1.17
     disproportionately
    1.10
     collectively
    1.08
     individually
    1.06
    selves
    1.04
     plentiful
    1.00
     routinely
    1.00
     interchangeable
    1.00
    Activations Density 8.921%

    No Known Activations