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

    Neuronpedia

    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 1536
    9. 8-RES_FS1536-JB
    11. 1128
    Prev
    Next
    INDEX
    Explanations

    information related to birth and pregnancy

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    343
    +0.10
    0.5%
    459
    +0.10
    0.5%
    78
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.12
    343
    +0.10
    0.08
    575
    +0.10
    0.10
    Negative Logits
     Flavoring
    -1.18
    atility
    -0.83
     lawy
    -0.78
    iance
    -0.73
    atile
    -0.73
    NRS
    -0.72
    ickr
    -0.71
    abulary
    -0.70
    olulu
    -0.69
    âĸ¬
    -0.68
    POSITIVE LOGITS
     childbirth
    0.96
    birth
    0.94
    days
    0.93
     babies
    0.88
    arenthood
    0.87
    mother
    0.85
    baby
    0.83
    Birth
    0.82
     daughter
    0.82
     baby
    0.79
    Activations Density 2.009%

    No Known Activations