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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18458
    Prev
    Next
    INDEX
    Explanations

    pronouns indicating relationships or connections between individuals

    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
    373
    +0.15
    0.7%
    504
    +0.10
    0.4%
    509
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    504
    +0.15
    0.01
    30
    +0.10
    0.01
    236
    +0.09
    0.01
    Negative Logits
    adobe
    -0.66
    LV
    -0.65
     ACPI
    -0.62
     Figures
    -0.62
    pez
    -0.62
    Interstitial
    -0.61
    DIT
    -0.59
    uci
    -0.59
    puter
    -0.59
    LESS
    -0.58
    POSITIVE LOGITS
    soever
    0.96
     regards
    0.64
     adjustment
    0.62
    usalem
    0.61
    arma
    0.61
    sey
    0.60
    terness
    0.60
    isen
    0.59
    isy
    0.57
     respect
    0.57
    Activations Density 0.024%

    No Known Activations