© 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 24576
    9. 8-RES_FS24576-JB
    11. 19512
    Prev
    Next
    INDEX
    Explanations

    facial features or related aspects like facial expressions and cosmetics

    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
    288
    +0.13
    0.6%
    715
    +0.09
    0.4%
    516
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    516
    +0.13
    0.01
    288
    +0.09
    0.01
    515
    +0.09
    0.01
    Negative Logits
    aday
    -0.88
    bare
    -0.85
    gard
    -0.80
    MQ
    -0.77
    uden
    -0.76
    cham
    -0.74
    nerg
    -0.73
     Provided
    -0.72
    HOU
    -0.72
    nesday
    -0.70
    POSITIVE LOGITS
     hair
    1.07
     expressions
    1.01
     recognition
    0.97
     portraits
    0.97
     tattoos
    0.95
     expression
    0.94
     impressions
    0.92
     muscles
    0.90
     makeup
    0.89
     prost
    0.88
    Activations Density 0.013%

    No Known Activations