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. 11557
    Prev
    Next
    INDEX
    Explanations

    quantities and measurements in recipes

    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
    302
    +0.11
    0.5%
    524
    +0.11
    0.5%
    683
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    524
    +0.11
    0.02
    589
    +0.11
    0.02
    302
    +0.10
    0.02
    Negative Logits
     Halls
    -0.77
    rights
    -0.76
    models
    -0.73
    projects
    -0.73
    gdala
    -0.73
     skelet
    -0.73
    suits
    -0.72
     halls
    -0.71
    endars
    -0.70
    humans
    -0.70
    POSITIVE LOGITS
     tsp
    1.04
     baking
    1.03
     vinegar
    1.02
     teaspoons
    0.95
     garlic
    0.95
     teaspoon
    0.94
     iod
    0.93
     cinnamon
    0.92
     potassium
    0.91
     salt
    0.89
    Activations Density 0.019%

    No Known Activations