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. 640
    Prev
    Next
    INDEX
    Explanations

    physical actions or events related to police and public interactions

    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
    553
    +0.10
    0.4%
    467
    +0.10
    0.4%
    673
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.10
    0.03
    419
    +0.10
    0.03
    553
    +0.09
    0.03
    Negative Logits
    ivals
    -0.80
    oday
    -0.70
    anguage
    -0.69
    hess
    -0.66
    ancies
    -0.66
    vae
    -0.65
    ships
    -0.65
    IUM
    -0.65
     Families
    -0.65
    requires
    -0.64
    POSITIVE LOGITS
    stretched
    0.90
     hers
    0.89
     clenched
    0.83
    ilts
    0.73
     protr
    0.73
     slit
    0.71
     palms
    0.70
     swollen
    0.69
     socket
    0.68
     shoulder
    0.68
    Activations Density 0.199%

    No Known Activations