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. 258
    Prev
    Next
    INDEX
    Explanations

    terms related to bodies of water and political rhetoric

    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
    607
    +0.12
    0.6%
    757
    +0.11
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.15
    232
    +0.11
    0.10
    326
    +0.10
    0.10
    Negative Logits
    Interstitial
    -0.93
    UGC
    -0.89
    haar
    -0.82
    ioch
    -0.82
    Bron
    -0.79
    ible
    -0.79
    ijah
    -0.75
    STEP
    -0.72
    chen
    -0.72
    ivable
    -0.72
    POSITIVE LOGITS
     shore
    1.11
     Islands
    1.03
     Seas
    0.97
     sailing
    0.97
     sailed
    0.96
    boat
    0.92
     Ocean
    0.91
     voyage
    0.91
     Kraken
    0.90
     fisherman
    0.90
    Activations Density 2.221%

    No Known Activations