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. 2834
    Prev
    Next
    INDEX
    Explanations

    financial and legal terms

    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
    630
    +0.10
    0.4%
    594
    +0.10
    0.4%
    496
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.14
    609
    +0.10
    0.09
    594
    +0.09
    0.08
    Negative Logits
    ––
    -0.74
    Ïī
    -0.73
     â̦"
    -0.73
    —"
    -0.71
    âĢķ
    -0.70
    .","
    -0.69
    ο
    -0.65
    .",
    -0.62
     thereof
    -0.61
    adr
    -0.61
    POSITIVE LOGITS
     Facts
    1.17
     Differences
    1.13
     Locations
    1.11
     Advice
    1.11
     Details
    1.11
     Features
    1.09
     Updates
    1.08
     Comparison
    1.08
     Overview
    1.07
     Problems
    1.07
    Activations Density 1.861%

    No Known Activations