© 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. 1020
    Prev
    Next
    INDEX
    Explanations

    French words or phrases

    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
    316
    +0.14
    0.6%
    384
    +0.11
    0.5%
    57
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.08
    316
    +0.11
    0.07
    60
    +0.10
    0.06
    Negative Logits
    ilial
    -0.83
     Wage
    -0.76
    ancial
    -0.74
    aceous
    -0.69
    ippy
    -0.68
     Flavoring
    -0.65
    icals
    -0.63
    mble
    -0.63
    ambers
    -0.62
    nikov
    -0.62
    POSITIVE LOGITS
    cember
    1.20
    arest
    1.10
    utsche
    1.06
     Blasio
    1.03
     facto
    1.02
    activated
    0.99
    utsch
    0.97
    legates
    0.96
    bris
    0.95
    ²¾
    0.95
    Activations Density 0.782%

    No Known Activations