© 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. 19358
    Prev
    Next
    INDEX
    Explanations

    words related to positive attributes or contributions

    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
    570
    +0.12
    0.5%
    441
    +0.10
    0.5%
    679
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    441
    +0.12
    0.02
    570
    +0.10
    0.01
    236
    +0.10
    0.02
    Negative Logits
    dar
    -0.78
     Lumpur
    -0.71
    mares
    -0.70
    creen
    -0.67
    corn
    -0.65
     Niet
    -0.64
    stall
    -0.63
    deal
    -0.63
    Availability
    -0.63
     Bran
    -0.61
    POSITIVE LOGITS
     thereto
    1.04
     materially
    0.86
     towards
    0.85
     positively
    0.84
    itives
    0.82
     generously
    0.81
     toward
    0.80
     contributions
    0.79
     greatly
    0.77
     immensely
    0.77
    Activations Density 0.035%

    No Known Activations