© 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. 11-RES-JB
    11. 13024
    Prev
    Next
    INDEX
    Explanations

    References to political leaders or figures in positions of authority

    oai_token-act-pair · gpt-3.5-turbo

    references to political leaders, particularly prime ministers

    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
     appendix
    -0.76
    iosis
    -0.73
     repe
    -0.66
     pole
    -0.63
     extras
    -0.63
     ashes
    -0.62
     juggling
    -0.62
     wipes
    -0.62
     simul
    -0.61
    bleacher
    -0.61
    POSITIVE LOGITS
     Minister
    1.67
     Ministers
    1.37
     minister
    1.25
     ministerial
    1.05
     ministers
    1.01
    Min
    0.95
     Min
    0.94
     Ministry
    0.92
     Affairs
    0.91
     Zeal
    0.89
    Activations Density 0.013%

    No Known Activations