© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 13919
    Prev
    Next
    INDEX
    Explanations

    the word "little" or related phrases which imply a small amount or degree

    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
    649
    +0.10
    0.5%
    344
    +0.10
    0.4%
    674
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.10
    0.04
    704
    +0.10
    0.03
    313
    +0.09
    0.03
    Negative Logits
    osponsors
    -0.84
    orthy
    -0.83
    ourses
    -0.81
    yss
    -0.78
    eneg
    -0.77
    yrim
    -0.75
    atars
    -0.75
    ADRA
    -0.75
    emort
    -0.74
    auld
    -0.74
    POSITIVE LOGITS
     bit
    1.48
     BIT
    0.87
     extra
    0.83
     patience
    0.79
     somet
    0.78
     Bit
    0.78
     girl
    0.76
     peek
    0.75
    bit
    0.75
     helper
    0.74
    Activations Density 0.031%

    No Known Activations