© 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. 5448
    Prev
    Next
    INDEX
    Explanations

    instances of words related to starting over or beginning anew

    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
    738
    +0.13
    0.6%
    471
    +0.12
    0.6%
    678
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.13
    0.05
    738
    +0.12
    0.04
    482
    +0.10
    0.04
    Negative Logits
     precincts
    -0.64
    obi
    -0.64
     entirety
    -0.61
    Origin
    -0.60
    itsch
    -0.59
    pedia
    -0.58
    phy
    -0.56
     wrought
    -0.56
    quickShipAvailable
    -0.55
     advancements
    -0.53
    POSITIVE LOGITS
     anew
    1.16
    nings
    0.87
    strap
    0.86
    ners
    0.83
     behaving
    0.80
    rek
    0.79
    angering
    0.77
     raining
    0.77
     worrying
    0.75
    ribune
    0.72
    Activations Density 0.076%

    No Known Activations