© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15817
    Prev
    Next
    INDEX
    Explanations

    names of individuals and specific terms for referencing people in a text

    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
    443
    +0.11
    0.5%
    320
    +0.10
    0.5%
    494
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.05
    494
    +0.10
    0.05
    46
    +0.10
    0.04
    Negative Logits
     tcp
    -0.63
    olulu
    -0.62
     ãģ
    -0.61
    į
    -0.59
    lehem
    -0.56
    ĻĤ
    -0.55
     mosquito
    -0.55
    ymm
    -0.55
     __
    -0.55
     php
    -0.54
    POSITIVE LOGITS
     himself
    1.52
     herself
    1.35
    enegger
    1.13
    's
    1.08
     Himself
    1.07
     Enterprises
    0.95
     Productions
    0.94
     Sr
    0.92
    tsy
    0.89
     Industries
    0.88
    Activations Density 0.205%

    No Known Activations