© 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. 10723
    Prev
    Next
    INDEX
    Explanations

    military-related terms and units

    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
    481
    +0.15
    0.7%
    513
    +0.10
    0.5%
    447
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.08
    537
    +0.10
    0.05
    225
    +0.10
    0.05
    Negative Logits
    paren
    -0.63
     Fountain
    -0.60
     Theft
    -0.60
     Parenthood
    -0.57
    verbs
    -0.57
    truth
    -0.57
    pport
    -0.57
     saline
    -0.57
     accur
    -0.57
     Wim
    -0.56
    POSITIVE LOGITS
    members
    1.41
     mates
    1.30
    mates
    1.27
     members
    1.23
     consisting
    1.21
     comprised
    1.19
     comprising
    1.19
    naire
    1.18
    rons
    1.15
    naires
    1.12
    Activations Density 0.391%

    No Known Activations