© 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. 12019
    Prev
    Next
    INDEX
    Explanations

    commands and configurations for managing servers and networks

    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
    373
    +0.24
    1.1%
    575
    +0.08
    0.4%
    660
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.24
    -0.05
    500
    +0.08
    0.04
    326
    +0.08
    0.07
    Negative Logits
    AUD
    -0.62
     growing
    -0.57
    Bloom
    -0.56
    kh
    -0.56
     firsthand
    -0.56
     surn
    -0.56
     domest
    -0.56
     grow
    -0.55
    ËĪ
    -0.54
    sung
    -0.53
    POSITIVE LOGITS
    earances
    0.73
    enment
    0.66
     Repeat
    0.65
    livion
    0.64
     [&
    0.62
    ement
    0.62
    ements
    0.59
     Normandy
    0.59
     guiName
    0.59
    urations
    0.58
    Activations Density 0.800%

    No Known Activations