Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 688
    Prev
    Next
    INDEX
    Explanations

    economic and financial 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_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
    481
    +0.13
    0.6%
    659
    +0.10
    0.4%
    630
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.14
    288
    +0.10
    0.19
    331
    +0.09
    0.12
    Negative Logits
    âĢķ
    -0.78
     â̦"
    -0.78
    Ïī
    -0.70
    â̦"
    -0.68
    ––
    -0.65
    â̦."
    -0.63
    )",
    -0.62
    ..."
    -0.62
     thereof
    -0.61
    —"
    -0.60
    POSITIVE LOGITS
     Differences
    0.92
     Comparison
    0.89
     Features
    0.88
     Profile
    0.88
     Thoughts
    0.85
     Analysis
    0.85
     Overview
    0.85
     Description
    0.83
     Examples
    0.83
     Locations
    0.82
    Activations Density 4.129%

    No Known Activations