© 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. 1-RES-JB
    11. 3562
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific politician or public figure

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific political figures, primarily Mayor Bill de Blasio

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioned
    -0.85
    full
    -0.78
    phal
    -0.67
    ãĥĨ
    -0.65
    fully
    -0.63
    bil
    -0.61
    RAW
    -0.61
    FU
    -0.61
    ional
    -0.61
    æѦ
    -0.60
    POSITIVE LOGITS
     Blasio
    1.41
     Cuomo
    0.98
    jriwal
    0.94
     Giuliani
    0.90
     Garc
    0.89
     shenan
    0.88
     Mellon
    0.80
    atton
    0.78
     oun
    0.77
     borough
    0.77
    Activations Density 0.009%

    No Known Activations