© 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. 11-RES-JB
    11. 1637
    Prev
    Next
    INDEX
    Explanations

    terms related to political elections

    oai_token-act-pair · gpt-3.5-turbo

    references to electoral outcomes and parliamentary elections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.72
     Frazier
    -0.71
    angelo
    -0.70
     leveled
    -0.69
    emis
    -0.65
    aylor
    -0.63
    bleacher
    -0.63
    ifact
    -0.63
    culosis
    -0.62
    jah
    -0.62
    POSITIVE LOGITS
     elections
    1.76
     parliamentary
    1.51
     election
    1.51
     Elections
    1.45
     polls
    1.42
     parliament
    1.36
     referendum
    1.34
     mayoral
    1.32
     electoral
    1.30
     Parliament
    1.27
    Activations Density 0.307%

    No Known Activations