© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 25947
    Prev
    Next
    INDEX
    Explanations

    monetary values and financial figures

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    241
    +0.11
    0.5%
    63
    +0.09
    0.4%
    340
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    230
    +0.11
    0.04
    352
    +0.09
    0.04
    495
    +0.09
    0.03
    Negative Logits
    soType
    -0.84
    terness
    -0.65
    iannopoulos
    -0.64
    sole
    -0.64
    alys
    -0.63
    udi
    -0.62
    ufact
    -0.61
    âĹ¼
    -0.60
    ovie
    -0.59
    esp
    -0.58
    POSITIVE LOGITS
    -$
    1.29
     apiece
    1.01
    /$
    0.97
     (£
    0.97
     USD
    0.92
    +
    0.91
    +.
    0.90
     per
    0.87
     crore
    0.84
     ($
    0.82
    Activations Density 0.041%

    No Known Activations