© 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. 15638
    Prev
    Next
    INDEX
    Explanations

    pronunciations of specific terms or names

    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
    473
    +0.12
    0.5%
    406
    +0.10
    0.4%
    557
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    603
    +0.12
    0.01
    609
    +0.10
    0.01
    473
    +0.10
    0.01
    Negative Logits
     Frie
    -0.73
    isconsin
    -0.73
    arte
    -0.72
    izons
    -0.69
    ebook
    -0.69
    ansas
    -0.69
    adr
    -0.69
    ashtra
    -0.67
    art
    -0.67
    tumblr
    -0.66
    POSITIVE LOGITS
     pronunciation
    1.07
     spelling
    1.02
     deaf
    0.94
    ciation
    0.94
     pronounce
    0.93
     phon
    0.93
     pronounced
    0.90
     vowel
    0.88
     pronoun
    0.84
     conson
    0.81
    Activations Density 0.041%

    No Known Activations