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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 12288
    9. 8-RES_FS12288-JB
    11. 10444
    Prev
    Next
    INDEX
    Explanations

    contractions of "are" and "have" as well as instances of "if" in text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    102
    +0.20
    1.0%
    566
    +0.18
    0.9%
    55
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.20
    0.11
    566
    +0.18
    0.11
    55
    +0.15
    0.11
    Negative Logits
    pedia
    -0.77
     Highlights
    -0.72
    ossom
    -0.71
    osate
    -0.69
     flourish
    -0.68
     chants
    -0.65
     strains
    -0.64
     Ensure
    -0.62
     Reports
    -0.62
     Extend
    -0.61
    POSITIVE LOGITS
     able
    1.32
     unable
    1.17
     aware
    1.17
     willing
    1.16
     afraid
    1.12
     unaware
    1.09
     unsure
    1.09
     lucky
    1.08
     obligated
    1.08
     tempted
    1.07
    Activations Density 0.393%

    No Known Activations