© 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. 6-RES-JB
    11. 12010
    Prev
    Next
    INDEX
    Explanations

    mentions of specific states in the context of political events

    oai_token-act-pair · gpt-3.5-turbo

    mentions of U.S. states and their relevance to political events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammers
    -0.82
    ĸļ
    -0.79
    ynt
    -0.77
     decomp
    -0.76
    cean
    -0.74
    TAG
    -0.74
    sonian
    -0.74
    merce
    -0.73
    ipedia
    -0.72
    vironment
    -0.71
    POSITIVE LOGITS
     Democratic
    1.02
     electorate
    1.01
     caucus
    0.94
     Republican
    0.91
     GOP
    0.88
     voters
    0.88
     polling
    0.86
     Governor
    0.85
     voting
    0.85
     caucuses
    0.84
    Activations Density 0.137%

    No Known Activations