© 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 1536
    9. 8-RES_FS1536-JB
    11. 1056
    Prev
    Next
    INDEX
    Explanations

    instances of significant change or transformation

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    642
    +0.12
    0.5%
    189
    +0.11
    0.5%
    288
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    642
    +0.12
    0.07
    189
    +0.11
    0.07
    658
    +0.11
    0.07
    Negative Logits
    amina
    -0.84
    ç«
    -0.68
    ngth
    -0.68
     Ys
    -0.64
     Goodman
    -0.64
     Huck
    -0.63
    trak
    -0.63
    True
    -0.62
    zees
    -0.62
    mination
    -0.61
    POSITIVE LOGITS
     drastically
    0.95
     radically
    0.91
     tack
    0.89
     gears
    0.86
    iating
    0.86
     dramatically
    0.83
    iations
    0.80
     effected
    0.78
     diapers
    0.76
    atile
    0.75
    Activations Density 1.700%

    No Known Activations