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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 163
    Prev
    Next
    INDEX
    Explanations

    phrases related to oil and gas extraction, exploration, and their associated controversies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    393
    +0.12
    0.5%
    398
    +0.11
    0.5%
    287
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    398
    +0.12
    0.11
    393
    +0.11
    0.14
    546
    +0.11
    0.10
    Negative Logits
    mberg
    -0.74
     Administ
    -0.73
    andowski
    -0.71
    Filename
    -0.68
     Collider
    -0.68
    Report
    -0.67
    ugi
    -0.66
     Investigator
    -0.66
    itatively
    -0.66
    actory
    -0.65
    POSITIVE LOGITS
     charcoal
    0.79
     linen
    0.77
     other
    0.75
     vinegar
    0.73
     Spice
    0.72
     mortar
    0.69
     booze
    0.69
     lime
    0.68
     potatoes
    0.67
     dairy
    0.67
    Activations Density 2.334%

    No Known Activations