© 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. 4949
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures

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

    references to government officials and their titles

    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
    EStream
    -0.78
    */(
    -0.76
    CLOSE
    -0.74
    eering
    -0.73
    DragonMagazine
    -0.73
    NOT
    -0.70
    ":"/
    -0.70
    dfx
    -0.69
    bleacher
    -0.68
    LESS
    -0.67
    POSITIVE LOGITS
     Carolyn
    1.02
     Mé
    1.02
     Laurel
    0.97
     Gerry
    0.97
     Melanie
    0.96
     Khalid
    0.94
     Jane
    0.93
     Bernard
    0.93
     Gord
    0.92
     Amar
    0.92
    Activations Density 0.042%

    No Known Activations