© 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. 1109
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to government, international relations, and social issues

    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
    497
    +0.11
    0.5%
    90
    +0.11
    0.5%
    130
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.11
    0.11
    130
    +0.11
    0.08
    258
    +0.10
    0.12
    Negative Logits
     Defin
    -0.54
     Klu
    -0.51
     Dangerous
    -0.51
    é¾įå
    -0.50
    é¾į
    -0.50
     namely
    -0.50
    product
    -0.49
     Piper
    -0.49
     acutely
    -0.48
     Canaver
    -0.48
    POSITIVE LOGITS
     etc
    1.41
    etc
    0.92
    ,
    0.84
    ,...
    0.82
     ect
    0.75
     &
    0.74
     and
    0.73
    !,
    0.69
    +,
    0.68
    ?,
    0.66
    Activations Density 2.918%

    No Known Activations