© 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. 24236
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ag."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    +0.14
    0.6%
    182
    +0.10
    0.4%
    659
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.14
    0.03
    659
    +0.10
    0.03
    232
    +0.10
    0.03
    Negative Logits
     Parenthood
    -0.69
    ignty
    -0.66
    pher
    -0.62
     tradem
    -0.60
     sclerosis
    -0.59
     nomine
    -0.57
    terday
    -0.56
     Tec
    -0.56
    birth
    -0.56
    theless
    -0.54
    POSITIVE LOGITS
    reement
    1.22
    glers
    1.17
    lia
    1.11
    gers
    1.10
    roup
    1.08
    allery
    1.06
    gered
    1.04
    hetto
    1.04
    azine
    1.01
    gy
    1.00
    Activations Density 0.036%

    No Known Activations