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. 1410
    Prev
    Next
    INDEX
    Explanations

    information related to smoking, cigarettes, lung cancer, and smoking meats

    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
    326
    +0.11
    0.5%
    255
    +0.09
    0.4%
    553
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.08
    288
    +0.09
    0.09
    232
    +0.09
    0.06
    Negative Logits
    wright
    -0.69
    assian
    -0.69
    SAY
    -0.69
     Agric
    -0.67
     acquisitions
    -0.65
     Defenders
    -0.65
    los
    -0.64
     Vanguard
    -0.63
    fol
    -0.62
    actionDate
    -0.61
    POSITIVE LOGITS
    oky
    1.09
     smoke
    0.99
     smoked
    0.96
     smoker
    0.93
     Smoke
    0.93
     cessation
    0.92
    okers
    0.89
     smoking
    0.89
     smokes
    0.88
     cigarettes
    0.86
    Activations Density 1.182%

    No Known Activations