© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 12084
    Prev
    Next
    INDEX
    Explanations

    mentions of the metaphorical concept of a "bucket list."

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    383
    +0.12
    0.5%
    420
    +0.11
    0.5%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.12
    0.01
    40
    +0.11
    0.01
    544
    +0.11
    0.01
    Negative Logits
    ournal
    -0.80
    uality
    -0.72
     Dominion
    -0.69
    âĸ¬
    -0.65
     Kham
    -0.65
    GGGGGGGG
    -0.64
    enegger
    -0.63
    egal
    -0.63
     Examiner
    -0.62
    eanor
    -0.61
    POSITIVE LOGITS
    loads
    1.00
    chest
    0.88
    pipe
    0.87
     bucket
    0.84
    cake
    0.84
    mates
    0.83
    hatt
    0.81
    alo
    0.81
    load
    0.80
     buckets
    0.80
    Activations Density 0.019%

    No Known Activations