© 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. 7583
    Prev
    Next
    INDEX
    Explanations

    internet-related content with potential legal or offensive implications, specifically related to social media comments or online behavior

    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
    481
    +0.17
    0.8%
    447
    +0.13
    0.6%
    576
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    725
    +0.17
    0.05
    576
    +0.13
    0.03
    439
    +0.12
    0.04
    Negative Logits
    urion
    -0.77
    cells
    -0.75
    ongevity
    -0.73
     endurance
    -0.71
    asio
    -0.70
     Ports
    -0.69
     Endurance
    -0.69
    byss
    -0.69
    ulton
    -0.69
     regeneration
    -0.68
    POSITIVE LOGITS
     derogatory
    1.34
     pornographic
    1.30
     blasp
    1.30
     insulting
    1.25
     objectionable
    1.23
     lewd
    1.20
     slurs
    1.18
     misogyn
    1.17
     hateful
    1.16
     swast
    1.15
    Activations Density 0.746%

    No Known Activations