© 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. 11-RES-JB
    11. 11427
    Prev
    Next
    INDEX
    Explanations

    names related to political figures

    oai_token-act-pair · gpt-3.5-turbo

    references to former political figures and their positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.74
     Grimoire
    -0.73
    ravings
    -0.70
     Riot
    -0.70
    raph
    -0.66
     warehouses
    -0.65
    alties
    -0.65
     queues
    -0.65
    Cra
    -0.65
    Mas
    -0.64
    POSITIVE LOGITS
     congressman
    1.37
     senator
    1.36
     governor
    1.28
     presidential
    1.23
     gubernatorial
    1.20
     Republican
    1.17
     GOP
    1.14
    Republican
    1.08
     Libertarian
    1.08
     Massachusetts
    1.07
    Activations Density 0.209%

    No Known Activations