© 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. 21048
    Prev
    Next
    INDEX
    Explanations

    phrases related to running for or seeking reelection in political positions

    oai_token-act-pair · gpt-3.5-turbo

    references to electoral candidacies and reelections

    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
     contrace
    -0.72
     acron
    -0.69
     Curve
    -0.62
    Chart
    -0.62
     Gleaming
    -0.61
     closure
    -0.60
    Pay
    -0.58
     Clockwork
    -0.58
     iceberg
    -0.58
    pload
    -0.56
    POSITIVE LOGITS
     2020
    1.00
    bernatorial
    0.94
    election
    0.90
     against
    0.89
    govtrack
    0.88
     someday
    0.85
     2018
    0.84
     2024
    0.84
     runoff
    0.83
     reelection
    0.82
    Activations Density 0.179%

    No Known Activations