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. 2812
    Prev
    Next
    INDEX
    Explanations

    complex social and political themes in textual content

    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
    481
    +0.32
    1.5%
    373
    +0.16
    0.8%
    67
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    67
    +0.32
    0.12
    97
    +0.16
    0.06
    481
    +0.11
    0.20
    Negative Logits
     nonetheless
    -0.76
    fortunately
    -0.74
     accordingly
    -0.73
     thereafter
    -0.73
    !.
    -0.61
     Pwr
    -0.60
    .[
    -0.60
    anwhile
    -0.58
    ."[
    -0.58
    .).
    -0.58
    POSITIVE LOGITS
     virginity
    0.62
    ?",
    0.61
    thood
    0.60
    wealth
    0.57
    gor
    0.57
    estamp
    0.56
    animate
    0.56
    zac
    0.55
     jerk
    0.55
     Guant
    0.55
    Activations Density 5.397%

    No Known Activations