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. 1474
    Prev
    Next
    INDEX
    Explanations

    information related to alcoholic beverages and brand names

    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
    609
    +0.10
    0.5%
    25
    +0.10
    0.5%
    71
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.10
    0.12
    344
    +0.10
    0.13
    748
    +0.09
    0.10
    Negative Logits
    asta
    -0.71
    lance
    -0.67
    vantage
    -0.67
     agre
    -0.67
    helps
    -0.67
     Caption
    -0.65
    IAS
    -0.65
    ULE
    -0.65
    geist
    -0.64
     srf
    -0.63
    POSITIVE LOGITS
    teenth
    1.77
    teen
    1.62
     hundred
    1.47
    fold
    1.35
    eenth
    1.33
     thousand
    1.29
    een
    1.24
     months
    1.16
     weeks
    1.16
    aciously
    1.12
    Activations Density 1.068%

    No Known Activations