© 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. 5425
    Prev
    Next
    INDEX
    Explanations

    dates in the format "Month, day" or "day, Year"

    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
    430
    +0.12
    0.6%
    301
    +0.11
    0.5%
    589
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    301
    +0.12
    0.04
    310
    +0.11
    0.04
    158
    +0.11
    0.04
    Negative Logits
    opic
    -0.84
     attachments
    -0.66
     VIDEOS
    -0.65
     grou
    -0.65
     predec
    -0.64
     diaper
    -0.64
     steroids
    -0.63
    vae
    -0.63
     brow
    -0.62
     bom
    -0.62
    POSITIVE LOGITS
     2017
    1.19
     2018
    1.17
     2015
    1.15
     2014
    1.14
     2016
    1.12
     âĶľ
    1.11
     2013
    1.09
     2012
    1.03
     2011
    1.01
     2010
    0.96
    Activations Density 0.052%

    No Known Activations