© 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. 3057
    Prev
    Next
    INDEX
    Explanations

    instances of sentences containing spelling errors

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.16
    0.8%
    481
    +0.10
    0.4%
    438
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.16
    0.03
    297
    +0.10
    0.03
    720
    +0.09
    0.04
    Negative Logits
    SourceFile
    -0.72
    Actor
    -0.63
    ighed
    -0.63
    coat
    -0.63
    ew
    -0.62
    ,
    -0.61
    stad
    -0.61
    rones
    -0.61
    RM
    -0.60
    front
    -0.59
    POSITIVE LOGITS
     somew
    0.66
     tacit
    0.64
     diminishing
    0.63
    utenberg
    0.60
    ilib
    0.59
    uana
    0.58
    decl
    0.56
    uct
    0.56
     rudimentary
    0.54
     withdrawing
    0.53
    Activations Density 0.144%

    No Known Activations