© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 20089
    Prev
    Next
    INDEX
    Explanations

    pattern matching or grouping related words based on similarity

    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
    314
    +0.13
    0.6%
    236
    +0.10
    0.5%
    529
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    130
    +0.13
    0.04
    90
    +0.10
    0.05
    288
    +0.10
    0.06
    Negative Logits
     similarly
    -0.65
     Prosecut
    -0.62
    nesday
    -0.61
     tremend
    -0.59
     Democr
    -0.59
     confir
    -0.58
     namely
    -0.58
    ©¶æ
    -0.55
     additionally
    -0.54
     Parables
    -0.54
    POSITIVE LOGITS
     etc
    1.04
    â̦)
    0.76
    ,
    0.75
     &
    0.62
    ,...
    0.60
    ...)
    0.60
    isma
    0.59
    ?,
    0.58
    ADRA
    0.57
    etc
    0.57
    Activations Density 0.257%

    No Known Activations