© 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. 3195
    Prev
    Next
    INDEX
    Explanations

    phrases indicating anticipation or expectation for the future

    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
    460
    +0.10
    0.5%
    718
    +0.10
    0.5%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.10
    0.03
    608
    +0.10
    0.03
    460
    +0.09
    0.02
    Negative Logits
     scanned
    -0.61
     FIR
    -0.60
     CPR
    -0.59
     mailing
    -0.58
     sts
    -0.55
     Subject
    -0.55
     quotation
    -0.54
     lying
    -0.54
     Jav
    -0.54
     activated
    -0.53
    POSITIVE LOGITS
    ilers
    1.10
    ggles
    0.94
    iler
    0.91
    iling
    0.90
    date
    0.87
    asters
    0.85
     determine
    0.85
     settle
    0.82
    ober
    0.81
    ilings
    0.81
    Activations Density 0.092%

    No Known Activations