© 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. 20711
    Prev
    Next
    INDEX
    Explanations

    dates

    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
    492
    +0.14
    0.6%
    469
    +0.13
    0.6%
    373
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.14
    -0.00
    241
    +0.13
    0.02
    469
    +0.12
    0.02
    Negative Logits
    conservancy
    -0.77
     corrid
    -0.76
    onge
    -0.76
    ritz
    -0.72
    iosyncr
    -0.69
    natureconservancy
    -0.68
    cffff
    -0.67
     forged
    -0.66
     tremend
    -0.65
    onse
    -0.64
    POSITIVE LOGITS
     February
    0.82
     Actress
    0.82
     January
    0.77
     December
    0.76
     TOTAL
    0.75
     Thumbnails
    0.75
     Accessories
    0.74
    BuyableInstoreAndOnline
    0.73
     Tul
    0.72
     June
    0.71
    Activations Density 0.031%

    No Known Activations