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 24576
    5. 8-RES_FS24576-JB
    6. 23561
    Prev
    Next
    INDEX
    Explanations

    terms related to nations and nationalism

    oai_token-act-pair · gpt-4o-miniTriggered 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
    420
    +0.12
    0.6%
    718
    +0.11
    0.5%
    76
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    414
    +0.12
    0.02
    436
    +0.11
    0.02
    718
    +0.09
    0.02
    Negative Logits
    IFT
    -0.67
    veyard
    -0.67
    urations
    -0.67
    door
    -0.66
    hift
    -0.64
    xual
    -0.63
    inventoryQuantity
    -0.63
    Berry
    -0.61
    omething
    -0.61
     pedals
    -0.60
    POSITIVE LOGITS
    wide
    1.00
    hood
    0.84
    States
    0.82
    strom
    0.78
    builder
    0.77
    rats
    0.75
    folk
    0.75
    sburg
    0.74
    eous
    0.74
     sovere
    0.74
    Activations Density 0.031%

    No Known Activations