© 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. 10295
    Prev
    Next
    INDEX
    Explanations

    terms related to gender identity and sexuality, particularly focusing on lesbianism, traditional gender roles, and societal perceptions of femininity

    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
    694
    +0.12
    0.6%
    614
    +0.09
    0.4%
    109
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.06
    314
    +0.09
    0.01
    232
    +0.09
    0.05
    Negative Logits
    etheless
    -0.95
     summary
    -0.75
    quartered
    -0.72
     dispatch
    -0.71
    lihood
    -0.70
     preliminary
    -0.68
    ensing
    -0.66
     âĵĺ
    -0.66
    £ı
    -0.65
     vigilance
    -0.65
    POSITIVE LOGITS
    ollywood
    1.00
    akespe
    0.95
    OOOO
    0.94
     Kardash
    0.92
    #$
    0.91
    ussian
    0.90
    zac
    0.90
    opoly
    0.90
    ussie
    0.87
    infeld
    0.84
    Activations Density 0.301%

    No Known Activations