© 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. 11838
    Prev
    Next
    INDEX
    Explanations

    phrases related to military operations and organizations

    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
    454
    +0.10
    0.5%
    104
    +0.10
    0.5%
    717
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    636
    +0.10
    0.03
    390
    +0.10
    0.03
    717
    +0.10
    0.03
    Negative Logits
    âĨij
    -0.84
    WARE
    -0.79
     bites
    -0.78
     ingestion
    -0.72
    bits
    -0.71
     loads
    -0.71
    licks
    -0.70
     scares
    -0.70
     clicks
    -0.69
     overe
    -0.68
    POSITIVE LOGITS
     Tanz
    0.84
     alliance
    0.81
     National
    0.80
     memorial
    0.79
     committees
    0.79
     federation
    0.79
     governing
    0.78
     nonprofit
    0.78
     caliphate
    0.77
     provisional
    0.77
    Activations Density 0.196%

    No Known Activations