© 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 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. 11-RES-JB
    11. 15486
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and election-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political figures and their electoral contexts

    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
     Bulg
    -0.77
    soType
    -0.71
     Yellowstone
    -0.66
     Loft
    -0.66
    igious
    -0.64
     SAM
    -0.62
     Sovereign
    -0.62
     Complex
    -0.62
     Scrib
    -0.61
    Ser
    -0.61
    POSITIVE LOGITS
     trailed
    1.44
     campaigned
    1.38
     trou
    1.33
     polled
    1.29
     surged
    1.27
     trails
    1.27
     defeated
    1.26
     outper
    1.22
     fared
    1.22
     garnered
    1.20
    Activations Density 0.253%

    No Known Activations