© 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. 4476
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal rights and issues related to discrimination

    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
    373
    +0.15
    0.7%
    300
    +0.11
    0.5%
    302
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.15
    0.04
    354
    +0.11
    0.04
    502
    +0.11
    0.04
    Negative Logits
     Flavoring
    -0.79
     Wad
    -0.69
    omatic
    -0.62
    awn
    -0.61
    Chel
    -0.60
     Kinn
    -0.60
     Camb
    -0.59
     Sussex
    -0.58
    uel
    -0.57
    aryl
    -0.57
    POSITIVE LOGITS
     shouldn
    1.12
     should
    1.02
    should
    0.91
     owed
    0.89
     ought
    0.88
    must
    0.86
     SHOULD
    0.84
     MUST
    0.84
     needed
    0.83
     must
    0.81
    Activations Density 0.191%

    No Known Activations