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. 45953
    Prev
    Next
    INDEX
    Explanations

    references to online activity and user engagement metrics

    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
    373
    +0.14
    0.7%
    385
    +0.11
    0.5%
    365
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    205
    +0.14
    0.01
    373
    +0.11
    0.00
    365
    +0.09
    0.01
    Negative Logits
    ibur
    -0.84
    mus
    -0.68
     Brun
    -0.68
    pas
    -0.65
    £ı
    -0.63
     Somers
    -0.63
     Ake
    -0.61
     Boe
    -0.61
     Dunk
    -0.61
     Fres
    -0.59
    POSITIVE LOGITS
    Merit
    1.26
    ertodd
    0.86
    ington
    0.73
    iculty
    0.69
    coins
    0.69
    Cash
    0.67
    bitcoin
    0.67
    lement
    0.67
    Shares
    0.66
    iciary
    0.65
    Activations Density 0.003%

    No Known Activations