© 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. 10-RES-JB
    11. 18754
    Prev
    Next
    INDEX
    Explanations

    mentions of political candidates and their campaigns

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political elections and candidates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sterdam
    -0.70
     Brach
    -0.69
    aimon
    -0.65
    MpServer
    -0.62
    Tang
    -0.62
     workshops
    -0.62
     acron
    -0.61
    enhagen
    -0.61
     Merchants
    -0.60
     scouts
    -0.60
    POSITIVE LOGITS
     presidency
    1.51
     presidential
    1.39
     nomination
    1.35
     nominee
    1.33
     Presidency
    1.33
     election
    1.28
     candidacy
    1.27
     reelection
    1.24
     2020
    1.19
     Election
    1.18
    Activations Density 0.314%

    No Known Activations