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 49152
    5. 8-RES_FS49152-JB
    6. 12110
    Prev
    Next
    INDEX
    Explanations

    numeric values and promotional pricing details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    573
    +0.15
    0.7%
    241
    +0.11
    0.5%
    128
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    573
    +0.15
    0.04
    495
    +0.11
    0.03
    165
    +0.10
    0.03
    Negative Logits
    unci
    -0.77
    arkable
    -0.71
    ittle
    -0.70
    ItemThumbnailImage
    -0.69
    cules
    -0.67
    oute
    -0.63
    igators
    -0.63
    quartered
    -0.62
    erning
    -0.62
    paio
    -0.62
    POSITIVE LOGITS
    -$
    1.28
    /$
    1.12
     USD
    0.93
     SOLD
    0.90
     Donation
    0.83
    USD
    0.82
     Quantity
    0.81
    /+
    0.78
     Minimum
    0.77
     Contributions
    0.77
    Activations Density 0.045%

    No Known Activations