© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11545
    Prev
    Next
    INDEX
    Explanations

    mentions of the political party GOP with a strong focus on support or criticism

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the GOP (Republican Party)

    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
    alam
    -0.80
     Baird
    -0.72
     Britann
    -0.71
     Manson
    -0.71
    isu
    -0.70
     Albion
    -0.69
     Gust
    -0.69
     Bulg
    -0.69
     Guinness
    -0.69
     Renault
    -0.67
    POSITIVE LOGITS
    roud
    1.23
     nominee
    1.05
     frontrunner
    1.05
     primaries
    1.00
     strategist
    0.97
     presidential
    0.96
    GOP
    0.96
     leadership
    0.95
     operative
    0.92
     orthodoxy
    0.91
    Activations Density 0.051%

    No Known Activations