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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 627
    Prev
    Next
    INDEX
    Explanations

    numbers and hyphenated phrases representing durations of time

    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
    672
    +0.12
    0.6%
    314
    +0.12
    0.6%
    97
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.12
    0.02
    260
    +0.12
    0.13
    97
    +0.11
    0.07
    Negative Logits
     Rica
    -0.69
     Dag
    -0.63
    terday
    -0.62
     Shutterstock
    -0.60
     fame
    -0.59
     substitutes
    -0.59
     Okawaru
    -0.58
     GEAR
    -0.58
    rencies
    -0.58
     adultery
    -0.57
    POSITIVE LOGITS
    %-
    0.85
    -
    0.85
    istine
    0.81
    bedroom
    0.78
     gallon
    0.77
    âĢij
    0.75
    ennial
    0.71
     dimensional
    0.71
    shapeshifter
    0.69
    taboola
    0.69
    Activations Density 2.382%

    No Known Activations