© 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 12288
    9. 8-RES_FS12288-JB
    11. 583
    Prev
    Next
    INDEX
    Explanations

    specific phrases referring to various computer programs and technical terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    +0.12
    0.5%
    636
    +0.11
    0.5%
    7
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.12
    -0.02
    232
    +0.11
    0.06
    284
    +0.10
    0.05
    Negative Logits
    CHO
    -0.65
     hoops
    -0.65
    ĨĴ
    -0.62
    MAR
    -0.61
     moms
    -0.59
    ylum
    -0.59
     IMAGES
    -0.58
     privileges
    -0.58
     HOME
    -0.58
     Neph
    -0.57
    POSITIVE LOGITS
    rations
    0.86
    ciating
    0.86
    idated
    0.80
    rating
    0.74
    ators
    0.71
    atable
    0.70
    rers
    0.69
    ushing
    0.69
    ator
    0.66
    ãĤ¨ãĥ«
    0.65
    Activations Density 0.295%

    No Known Activations