© 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. 13451
    Prev
    Next
    INDEX
    Explanations

    commands or prompts related to an item exchange or refund

    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
    640
    +0.29
    1.5%
    314
    +0.24
    1.2%
    447
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.29
    0.11
    160
    +0.24
    0.10
    442
    +0.17
    0.09
    Negative Logits
     Mub
    -0.75
     camp
    -0.74
     reb
    -0.72
     grop
    -0.72
     ramp
    -0.71
     scrap
    -0.71
     frontline
    -0.71
     mull
    -0.71
     campaigns
    -0.70
     freel
    -0.70
    POSITIVE LOGITS
    RAW
    1.82
    Loading
    1.68
    Topic
    1.44
    Advertisements
    1.37
    Topics
    1.36
    Reviewer
    1.35
    Posted
    1.33
    Introduction
    1.33
    {"
    1.30
    Trivia
    1.29
    Activations Density 0.255%

    No Known Activations