© 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. 15560
    Prev
    Next
    INDEX
    Explanations

    an emphasis on appreciation and acknowledgment

    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
    481
    +0.16
    0.8%
    523
    +0.10
    0.5%
    264
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.16
    0.05
    338
    +0.10
    0.04
    45
    +0.10
    0.03
    Negative Logits
    ESE
    -0.78
    ãĤ´ãĥ³
    -0.70
    cade
    -0.65
    odcast
    -0.64
    quished
    -0.64
     Corpus
    -0.63
    OSH
    -0.62
    Tip
    -0.62
    ajo
    -0.61
    trak
    -0.61
    POSITIVE LOGITS
     consequ
    0.79
     willingness
    0.76
     alike
    0.72
     consequently
    0.70
     timetable
    0.66
     therefore
    0.66
     courage
    0.63
     hopefully
    0.62
     corresponding
    0.62
     nets
    0.61
    Activations Density 0.259%

    No Known Activations