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

    Neuronpedia

    Jacobian LensNEW
    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. 9035
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing criminal activities or controversies

    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
    480
    +0.32
    1.5%
    447
    +0.16
    0.8%
    523
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.32
    0.07
    642
    +0.16
    0.03
    480
    +0.10
    -0.01
    Negative Logits
    !'
    -0.82
    !'"
    -0.65
    )'
    -0.60
     Fuck
    -0.60
    schild
    -0.59
    .'
    -0.59
    ?'
    -0.59
     Illust
    -0.56
    .'"
    -0.55
     Writ
    -0.54
    POSITIVE LOGITS
     "
    0.94
     "âĢ¦
    0.92
     "...
    0.89
     "[
    0.89
     "'
    0.84
     ''
    0.77
     "(
    0.72
     "#
    0.69
     counselling
    0.64
     misunderstood
    0.64
    Activations Density 1.082%

    No Known Activations