© 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 EvalsExportsinterp-engineNEWAPI 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. 20626
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals being accused of wrongdoing or facing criticism

    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
    699
    +0.10
    0.5%
    694
    +0.10
    0.5%
    652
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    686
    +0.10
    0.05
    526
    +0.10
    -0.01
    711
    +0.10
    0.03
    Negative Logits
     Provincial
    -0.69
    displayText
    -0.69
     Printed
    -0.65
     Regional
    -0.64
    lished
    -0.63
     convened
    -0.63
     Procedures
    -0.61
     Audit
    -0.61
     Jur
    -0.60
     Regulatory
    -0.60
    POSITIVE LOGITS
    sexual
    0.80
    acid
    0.76
     raping
    0.74
     virginity
    0.74
    thood
    0.72
    alien
    0.70
     sexually
    0.70
     genitals
    0.69
     vagina
    0.68
     apes
    0.68
    Activations Density 1.635%

    No Known Activations