© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 7493
    Prev
    Next
    INDEX
    Explanations

    references to political elections

    oai_token-act-pair · gpt-3.5-turbo

    references to elections and voting processes

    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
     Fargo
    -0.75
     Georgetown
    -0.73
     Patterson
    -0.70
    avery
    -0.68
     Fortune
    -0.68
    Jr
    -0.65
    Texas
    -0.65
     Lynch
    -0.65
     Arlington
    -0.64
     Mercer
    -0.64
    POSITIVE LOGITS
     elections
    1.08
     election
    1.03
     polls
    0.99
     organisers
    0.97
     favourites
    0.97
    eering
    0.95
     manifesto
    0.93
    election
    0.90
     electoral
    0.87
     Elections
    0.86
    Activations Density 0.070%

    No Known Activations