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 3072
    5. 8-RES_FS3072-JB
    6. 1482
    Prev
    Next
    INDEX
    Explanations

    semicolons used as a punctuation cue for emphasis or separation within a sentence or list

    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
    679
    +0.12
    0.6%
    614
    +0.12
    0.5%
    587
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.12
    0.04
    587
    +0.12
    0.05
    614
    +0.12
    0.04
    Negative Logits
    orts
    -0.77
    din
    -0.72
    stration
    -0.71
    inki
    -0.70
    ractions
    -0.69
     resil
    -0.69
    omorphic
    -0.68
    agic
    -0.68
    ricular
    -0.67
    ħĭ
    -0.67
    POSITIVE LOGITS
    -)
    1.16
     alternatively
    1.06
     furthermore
    1.03
    âĢ¢âĢ¢âĢ¢âĢ¢
    0.98
     moreover
    0.97
     namely
    0.93
     alas
    0.91
     consequently
    0.90
     hence
    0.90
     thence
    0.89
    Activations Density 0.266%

    No Known Activations