© 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. 9-RES-JB
    11. 11489
    Prev
    Next
    INDEX
    Explanations

    mentions of political polls and election statistics

    oai_token-act-pair · gpt-3.5-turbo

    polling data and statistics related to political candidates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obyl
    -0.83
    assetsadobe
    -0.74
    aundering
    -0.69
     Cheap
    -0.68
     smugglers
    -0.66
     Zamb
    -0.66
    ichick
    -0.65
     laundering
    -0.65
     Arbit
    -0.63
     Tibetan
    -0.63
    POSITIVE LOGITS
     undecided
    1.08
     majorities
    0.99
     Gallup
    0.98
     polling
    0.97
     polled
    0.97
     independents
    0.95
     Libertarian
    0.92
     margin
    0.92
    Republicans
    0.91
     polls
    0.91
    Activations Density 0.258%

    No Known Activations