© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 2006
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names, particularly "Ivanka" and "Kushner"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Trump family, specifically Ivanka Trump and Jared Kushner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     experiment
    -0.69
     worm
    -0.69
     sap
    -0.68
    bugs
    -0.67
     Slayer
    -0.67
     Demons
    -0.64
    AU
    -0.64
     suff
    -0.61
     Trou
    -0.60
     decom
    -0.59
    POSITIVE LOGITS
     Ivanka
    3.94
     Kushner
    2.63
     Melania
    2.25
    Iv
    2.23
    TRUMP
    1.62
     TRUMP
    1.51
     Trump
    1.50
    Trump
    1.47
     Bannon
    1.43
     Tiffany
    1.36
    Activations Density 0.017%

    No Known Activations