© 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. 2957
    Prev
    Next
    INDEX
    Explanations

    comparative descriptions regarding physical attributes or qualities

    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
    455
    +0.13
    0.6%
    571
    +0.10
    0.5%
    321
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.13
    0.05
    387
    +0.10
    0.04
    262
    +0.10
    0.03
    Negative Logits
    advertising
    -0.78
    ainted
    -0.76
    EVA
    -0.73
    EP
    -0.70
    hack
    -0.68
     WATCHED
    -0.68
    este
    -0.68
    shire
    -0.65
    hr
    -0.65
    anova
    -0.63
    POSITIVE LOGITS
     than
    1.74
     Than
    1.53
    than
    1.51
     "$:/
    0.90
     versions
    0.85
    iating
    0.85
     Faster
    0.77
     brother
    0.68
     sibling
    0.68
    iator
    0.67
    Activations Density 0.080%

    No Known Activations