© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3966
    Prev
    Next
    INDEX
    Explanations

    information related to historical events or individuals and popular culture references

    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
    598
    +0.12
    0.5%
    481
    +0.11
    0.5%
    408
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    598
    +0.12
    0.07
    203
    +0.11
    0.06
    417
    +0.10
    0.06
    Negative Logits
    è¦ļéĨĴ
    -0.80
    ilaterally
    -0.73
    umat
    -0.71
    untary
    -0.70
    awi
    -0.68
    PA
    -0.67
    verbal
    -0.67
    Optional
    -0.65
    edu
    -0.65
    azeera
    -0.64
    POSITIVE LOGITS
     alas
    1.29
     beware
    1.04
     unfortunately
    0.96
     sadly
    0.89
     amidst
    0.85
     luckily
    0.85
     fortunately
    0.84
     lately
    0.83
    tons
    0.83
    chers
    0.83
    Activations Density 0.251%

    No Known Activations