© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2418
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events and candidates in the Democratic party

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    mentions of political endorsements and the Democratic primary process

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Sultan
    -1.08
     Lumpur
    -0.98
     Allaah
    -0.96
     Kuala
    -0.91
     Constantinople
    -0.88
     Istanbul
    -0.86
     Ottoman
    -0.84
     Yaz
    -0.83
     Malays
    -0.82
     turkey
    -0.82
    POSITIVE LOGITS
     Sanders
    2.65
    Sanders
    2.60
    Bernie
    2.27
     Bernie
    2.16
     Vermont
    1.75
     Burlington
    1.64
    Clinton
    1.51
     Clinton
    1.43
    Hillary
    1.33
     DNC
    1.31
    Activations Density 0.414%

    No Known Activations