© 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. 7928
    Prev
    Next
    INDEX
    Explanations

    information related to government actions and policies

    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
    762
    +0.12
    0.6%
    637
    +0.11
    0.5%
    679
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.12
    0.06
    455
    +0.11
    0.05
    679
    +0.11
    0.06
    Negative Logits
    anny
    -0.74
    ouf
    -0.69
    ople
    -0.67
    utenant
    -0.65
     Unle
    -0.64
    ructose
    -0.63
    irst
    -0.63
    Accessory
    -0.61
    iasis
    -0.60
    Quantity
    -0.59
    POSITIVE LOGITS
     besides
    1.18
     similarly
    1.07
     similar
    0.91
    worldly
    0.85
     equally
    0.85
     fared
    0.85
     likewise
    0.78
     than
    0.75
     includ
    0.73
     such
    0.71
    Activations Density 0.427%

    No Known Activations