© 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. 1537
    Prev
    Next
    INDEX
    Explanations

    terms related to the feeling of disgust

    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
    299
    +0.10
    0.5%
    639
    +0.10
    0.5%
    756
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.10
    0.04
    232
    +0.10
    0.03
    639
    +0.10
    0.03
    Negative Logits
     smack
    -0.68
     hypers
    -0.62
     congr
    -0.62
     livest
    -0.61
     lapse
    -0.59
     hypot
    -0.59
    Ô
    -0.58
    arella
    -0.57
     Noah
    -0.56
     neoc
    -0.56
    POSITIVE LOGITS
    owship
    1.02
    ption
    0.96
    ction
    0.87
    ointed
    0.83
    ptives
    0.81
    ivable
    0.81
    untled
    0.80
    atives
    0.79
    ptive
    0.79
    cling
    0.78
    Activations Density 0.144%

    No Known Activations