© 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 24576
    9. 8-RES_FS24576-JB
    11. 6666
    Prev
    Next
    INDEX
    Explanations

    social media follow prompts

    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
    679
    +0.17
    0.8%
    373
    +0.13
    0.6%
    613
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    359
    +0.17
    0.02
    613
    +0.13
    0.02
    357
    +0.10
    0.02
    Negative Logits
    ãĥ´ãĤ¡
    -0.68
    pite
    -0.68
    cit
    -0.68
    endiary
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.64
    anyon
    -0.63
    venge
    -0.62
    bably
    -0.61
    inese
    -0.61
    minist
    -0.60
    POSITIVE LOGITS
     Follow
    0.86
     @
    0.85
    ership
    0.83
     Stories
    0.82
    ers
    0.81
     Updates
    0.76
    Follow
    0.74
     Trend
    0.73
     Inqu
    0.71
     updates
    0.70
    Activations Density 0.017%

    No Known Activations