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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1917
    Prev
    Next
    INDEX
    Explanations

    specific references to elections, including mentions of different types of elections (local, presidential, parliamentary) and related terms like candidates and results

    oai_token-act-pair · gpt-3.5-turbo

    references to various elections and electoral processes

    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
    omorph
    -0.66
    Factor
    -0.65
    ãĤĮ
    -0.61
     Cable
    -0.61
     Patterson
    -0.61
    Ku
    -0.61
     Georgetown
    -0.60
     Flavoring
    -0.60
    use
    -0.60
     Bree
    -0.59
    POSITIVE LOGITS
    eering
    1.23
     elections
    1.08
     polls
    1.01
     campaigns
    0.91
     election
    0.91
    election
    0.88
     manifesto
    0.88
     runoff
    0.87
     campaign
    0.86
     Elections
    0.85
    Activations Density 0.048%

    No Known Activations