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. 904
    Prev
    Next
    INDEX
    Explanations

    verbs related to ability, capability, or possibility

    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
    7
    +0.10
    0.4%
    490
    +0.09
    0.4%
    4
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.10
    0.09
    490
    +0.09
    0.07
    4
    +0.09
    0.07
    Negative Logits
     Parents
    -0.69
     Tradition
    -0.62
    email
    -0.60
    aternity
    -0.60
    rium
    -0.58
    friend
    -0.57
    adish
    -0.57
     Nose
    -0.56
    dress
    -0.56
    dad
    -0.54
    POSITIVE LOGITS
    bodied
    1.01
    ioned
    0.95
     to
    0.76
     ta
    0.76
    Reviewer
    0.75
     bod
    0.74
    reys
    0.72
     compe
    0.69
     simultane
    0.69
     Osw
    0.67
    Activations Density 1.517%

    No Known Activations