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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16740
    Prev
    Next
    INDEX
    Explanations

    text related to political elections, especially "midterm elections" and "reelection."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of political events, specifically midterm and reelection occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ijk
    -0.79
    pots
    -0.77
    orld
    -0.77
    resp
    -0.72
    king
    -0.71
    SOURCE
    -0.70
    rawling
    -0.69
    rosis
    -0.68
    itsch
    -0.67
    âĵĺ
    -0.66
    POSITIVE LOGITS
     midterm
    1.00
     elections
    0.93
     election
    0.83
     slump
    0.81
     Election
    0.80
     tightening
    0.80
     electorate
    0.79
    é¾įå¥ij士
    0.75
     reelection
    0.75
    ratulations
    0.73
    Activations Density 0.007%

    No Known Activations