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. 1210
    Prev
    Next
    INDEX
    Explanations

    mentions of states in the context of food distribution and medical incidents

    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
    566
    +0.10
    0.4%
    643
    +0.10
    0.4%
    588
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    643
    +0.10
    0.01
    11
    +0.10
    0.01
    65
    +0.09
    0.01
    Negative Logits
    Ü
    -0.79
    ÃŃa
    -0.77
    vous
    -0.76
    arently
    -0.76
     Seym
    -0.73
    ovych
    -0.73
    ichick
    -0.73
    theless
    -0.71
    yss
    -0.70
    etry
    -0.70
    POSITIVE LOGITS
    inois
    1.10
     Masonic
    0.97
     Tribune
    0.87
     Illinois
    0.80
     Rapids
    0.78
     State
    0.77
     Cubs
    0.77
     Meadows
    0.77
     Wesley
    0.77
     Pacers
    0.76
    Activations Density 0.015%

    No Known Activations