© 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. 21169
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "each" in the 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
    756
    +0.12
    0.6%
    214
    +0.11
    0.5%
    216
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    216
    +0.12
    0.04
    614
    +0.11
    0.03
    214
    +0.11
    0.03
    Negative Logits
    letters
    -0.68
    tops
    -0.63
    models
    -0.62
    marks
    -0.60
    rovers
    -0.59
    veyard
    -0.59
    hawks
    -0.58
    renheit
    -0.58
    gur
    -0.57
    oute
    -0.57
    POSITIVE LOGITS
    other
    1.03
     successive
    1.00
     individually
    0.91
     individual
    0.86
     iteration
    0.85
     respective
    0.84
    malink
    0.78
     element
    0.77
     person
    0.76
     ounce
    0.74
    Activations Density 0.036%

    No Known Activations