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. 175
    Prev
    Next
    INDEX
    Explanations

    scientific research-related terms and concepts

    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
    578
    +0.12
    0.5%
    574
    +0.11
    0.5%
    644
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.12
    575
    +0.11
    0.11
    235
    +0.10
    0.09
    Negative Logits
    erous
    -0.68
     timers
    -0.65
    veland
    -0.61
    zik
    -0.60
     Yanuk
    -0.60
    cakes
    -0.59
     Rapids
    -0.59
     chant
    -0.59
     Remastered
    -0.58
     chopped
    -0.56
    POSITIVE LOGITS
    sonian
    1.00
    Researchers
    0.94
     Researchers
    0.94
     resear
    0.87
     scientist
    0.87
     researcher
    0.84
     research
    0.84
     Scientist
    0.84
     physicist
    0.83
     laboratories
    0.82
    Activations Density 1.714%

    No Known Activations