© 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. 2977
    Prev
    Next
    INDEX
    Explanations

    names of social media platforms

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    447
    +0.25
    1.2%
    481
    +0.21
    1.0%
    343
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.25
    0.04
    508
    +0.21
    0.03
    294
    +0.12
    0.03
    Negative Logits
     Dise
    -0.66
    cised
    -0.64
    lass
    -0.63
    inav
    -0.61
    ttes
    -0.59
    othy
    -0.59
    atche
    -0.59
    ~~~~~~~~~~~~~~~~
    -0.58
    zin
    -0.57
    fee
    -0.57
    POSITIVE LOGITS
     Messenger
    0.93
    nect
    0.86
     Analytics
    0.82
     Labs
    0.78
     Corporation
    0.76
     users
    0.75
     CEO
    0.74
     user
    0.73
    bots
    0.73
    Money
    0.72
    Activations Density 0.054%

    No Known Activations