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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7220
    Prev
    Next
    INDEX
    Explanations

    dates

    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
    301
    +0.13
    0.6%
    443
    +0.11
    0.5%
    306
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    306
    +0.13
    0.04
    301
    +0.11
    0.04
    443
    +0.10
    0.03
    Negative Logits
    ggle
    -0.80
    ught
    -0.74
    arantine
    -0.72
    ensical
    -0.72
    wcs
    -0.71
    nces
    -0.70
    cffff
    -0.69
     ancest
    -0.68
    fect
    -0.66
    itton
    -0.66
    POSITIVE LOGITS
    eenth
    1.09
    mented
    1.07
     2018
    0.99
     2017
    0.98
     Ames
    0.94
     2015
    0.93
     2014
    0.91
     2016
    0.90
     2013
    0.89
    sburg
    0.85
    Activations Density 0.017%

    No Known Activations