© 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 24576
    9. 8-RES_FS24576-JB
    11. 14846
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial struggles and negotiations

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    480
    +0.41
    2.0%
    665
    +0.11
    0.5%
    53
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.41
    0.09
    480
    +0.11
    0.01
    362
    +0.09
    0.07
    Negative Logits
    fortunately
    -0.69
    xtap
    -0.66
     Variant
    -0.62
     notation
    -0.61
    kson
    -0.59
    emed
    -0.58
     volunteered
    -0.58
    Notice
    -0.58
     surpr
    -0.58
     Instructor
    -0.58
    POSITIVE LOGITS
     ObamaCare
    0.84
     2020
    0.83
    Brexit
    0.82
     Brexit
    0.82
     overhaul
    0.81
     economically
    0.79
     reforms
    0.78
     2019
    0.76
    ordable
    0.76
     sustainable
    0.74
    Activations Density 0.798%

    No Known Activations