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 768
    5. 8-RES_FS768-JB
    6. 168
    Prev
    Next
    INDEX
    Explanations

    topics related to community events and initiatives, particularly focused on improving public safety and enhancing neighborhood connections

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs768-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    768
    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
    314
    +0.16
    0.7%
    566
    +0.13
    0.6%
    320
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.16
    0.13
    659
    +0.13
    0.13
    392
    +0.12
    0.13
    Negative Logits
    hold
    -0.77
    flies
    -0.76
     ç¥ŀ
    -0.71
    geons
    -0.70
    ré
    -0.68
    lets
    -0.68
    selling
    -0.65
     Notting
    -0.62
    esville
    -0.61
    zai
    -0.60
    POSITIVE LOGITS
    FU
    1.33
    AR
    1.32
    KI
    1.30
    AT
    1.29
    IC
    1.29
    BC
    1.29
    RA
    1.28
    OD
    1.27
    OC
    1.27
    TF
    1.27
    Activations Density 2.179%

    No Known Activations