© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 11912
    Prev
    Next
    INDEX
    Explanations

    phrases or mentions related to a specific person named Angela

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Angela Merkel

    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
    QU
    -0.70
     Utah
    -0.69
    icut
    -0.69
     reserves
    -0.67
     QU
    -0.66
     query
    -0.66
     Liqu
    -0.66
    oval
    -0.66
     tract
    -0.65
     Salt
    -0.65
    POSITIVE LOGITS
     Angela
    3.64
     Merkel
    1.57
     Diane
    1.42
     Theresa
    1.41
     Lena
    1.35
     Heather
    1.33
     Sophie
    1.33
     Suzanne
    1.32
     Carmen
    1.30
     Margaret
    1.30
    Activations Density 0.018%

    No Known Activations