© 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 12288
    9. 8-RES_FS12288-JB
    11. 10569
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns indicating possession

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    362
    +0.13
    0.6%
    541
    +0.10
    0.5%
    597
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.13
    0.07
    541
    +0.10
    0.06
    553
    +0.10
    0.04
    Negative Logits
    ablishment
    -0.72
    Chall
    -0.72
     Aren
    -0.68
    UNCH
    -0.68
     hereafter
    -0.67
     Rowling
    -0.65
    wik
    -0.65
    ozy
    -0.64
    nown
    -0.64
    forth
    -0.63
    POSITIVE LOGITS
     own
    1.69
     fingers
    1.22
     fists
    1.15
     knees
    1.14
    selves
    1.09
     legs
    1.09
     toes
    1.08
     elbows
    1.06
     sleeves
    1.04
     arms
    1.03
    Activations Density 0.254%

    No Known Activations