© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 20392
    Prev
    Next
    INDEX
    Explanations

    references to political figures, especially chancellors like Angela Merkel and George Osborne

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political leaders, specifically chancellors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.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

    Negative Logits
    ibaba
    -0.86
    Americans
    -0.84
    kinson
    -0.77
    avery
    -0.72
    ities
    -0.72
    yrinth
    -0.71
    trak
    -0.71
    ioned
    -0.69
    cki
    -0.69
    avez
    -0.68
    POSITIVE LOGITS
    llor
    1.42
     Chancellor
    1.02
     chancellor
    0.95
     Merkel
    0.92
     Angela
    0.90
     emer
    0.67
     Carol
    0.66
     Ann
    0.64
     Clicker
    0.63
    ãģ®å®
    0.62
    Activations Density 0.025%

    No Known Activations