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. 1278
    Prev
    Next
    INDEX
    Explanations

    information related to internet content creation and search engine optimization

    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
    269
    +0.12
    0.5%
    169
    +0.10
    0.5%
    302
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.11
    326
    +0.10
    0.10
    143
    +0.10
    0.06
    Negative Logits
    Production
    -0.76
    ivari
    -0.73
     Leilan
    -0.69
    nect
    -0.67
    terness
    -0.62
    ocard
    -0.62
    inki
    -0.61
    roach
    -0.61
    ews
    -0.61
    iah
    -0.60
    POSITIVE LOGITS
    sonian
    0.84
    finder
    0.79
     searches
    0.73
    ging
    0.72
    emouth
    0.72
    mage
    0.72
    ãĤ¦ãĤ¹
    0.71
     warrant
    0.71
     sear
    0.71
    ARCH
    0.70
    Activations Density 2.193%

    No Known Activations