© 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. 12000
    Prev
    Next
    INDEX
    Explanations

    dates of publications or events

    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
    183
    +0.14
    0.6%
    545
    +0.11
    0.5%
    746
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    183
    +0.14
    0.02
    545
    +0.11
    0.01
    106
    +0.09
    0.01
    Negative Logits
    porary
    -0.73
    adra
    -0.73
    umatic
    -0.70
    perture
    -0.65
    utic
    -0.65
    iors
    -0.65
    ilogy
    -0.65
    antics
    -0.64
    thora
    -0.64
    otropic
    -0.63
    POSITIVE LOGITS
     VIDEOS
    0.71
     Tue
    0.69
     weekday
    0.69
     Thu
    0.65
     aloud
    0.65
     Date
    0.64
    aturdays
    0.64
     04
    0.62
     hrs
    0.62
    week
    0.61
    Activations Density 0.018%

    No Known Activations