Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 2787
    Prev
    Next
    INDEX
    Explanations

    baking instructions and food 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_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
    55
    +0.13
    0.6%
    393
    +0.13
    0.6%
    537
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.13
    0.08
    0
    +0.13
    0.07
    393
    +0.10
    0.08
    Negative Logits
    ETS
    -0.92
    ESE
    -0.90
    ortmund
    -0.81
    YS
    -0.81
    okia
    -0.80
    SHIP
    -0.79
    asio
    -0.79
    EStream
    -0.79
    olphins
    -0.79
    iage
    -0.78
    POSITIVE LOGITS
     adventurous
    1.07
     efficient
    1.06
     unpredictable
    1.05
     economical
    1.04
     fearless
    1.04
     flavorful
    1.04
     energetic
    1.00
    rogen
    0.99
     inclusive
    0.99
     insightful
    0.97
    Activations Density 0.679%

    No Known Activations