© 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. 10519
    Prev
    Next
    INDEX
    Explanations

    social and political issues related to law enforcement, prisons, and government

    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
    618
    +0.14
    0.6%
    679
    +0.12
    0.5%
    640
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.14
    0.16
    679
    +0.12
    0.14
    440
    +0.11
    0.12
    Negative Logits
     canon
    -0.84
    omics
    -0.79
    ŃĶ
    -0.77
    éŃĶ
    -0.72
     brief
    -0.72
    ernaut
    -0.72
     officially
    -0.72
     abyss
    -0.71
     comprehens
    -0.71
     defe
    -0.70
    POSITIVE LOGITS
     Often
    1.50
     Sometimes
    1.50
     Occasionally
    1.38
     Others
    1.32
     Conversely
    1.29
     Examples
    1.25
     Usually
    1.24
     Eventually
    1.23
     Typically
    1.22
     Similarly
    1.22
    Activations Density 0.830%

    No Known Activations