© 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. 8-RES-JB
    11. 19076
    Prev
    Next
    INDEX
    Explanations

    references to or mentions of political figures with the title "Senator"

    oai_token-act-pair · gpt-3.5-turbo

    the term "Senator" and variations of it along with related rankings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     upkeep
    -0.71
     behavi
    -0.67
     curfew
    -0.64
    phal
    -0.63
    اÙĦ
    -0.62
    heading
    -0.61
     traffickers
    -0.61
    tera
    -0.60
    iHUD
    -0.59
    puted
    -0.58
    POSITIVE LOGITS
     Dianne
    0.96
    arians
    0.94
    pai
    0.93
    ileaks
    0.92
    ial
    0.90
    iors
    0.87
     Senator
    0.86
    hips
    0.85
     Grassley
    0.85
     Schumer
    0.85
    Activations Density 0.029%

    No Known Activations