© 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 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. 11081
    Prev
    Next
    INDEX
    Explanations

    instances of the word "something"

    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
    739
    +0.11
    0.5%
    701
    +0.10
    0.4%
    538
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    40
    +0.11
    0.04
    13
    +0.10
    0.04
    701
    +0.09
    0.03
    Negative Logits
    DOS
    -0.81
    ardi
    -0.70
    ude
    -0.69
    inders
    -0.69
    ortex
    -0.66
    ilt
    -0.66
    anos
    -0.66
    orks
    -0.66
    phones
    -0.64
    ildo
    -0.63
    POSITIVE LOGITS
     else
    1.48
    Else
    1.34
     resembling
    1.18
     intangible
    0.95
     akin
    0.93
     Else
    0.89
    iverse
    0.88
     miraculous
    0.88
    else
    0.86
     tangible
    0.86
    Activations Density 0.056%

    No Known Activations