© 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. 18567
    Prev
    Next
    INDEX
    Explanations

    mentions of political elections, particularly the 2016 election

    oai_token-act-pair · gpt-3.5-turbo

    references to elections and the associated political context

    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
    isu
    -0.87
    afety
    -0.72
    mbuds
    -0.71
    onga
    -0.68
    URA
    -0.68
    oba
    -0.65
    DEP
    -0.65
    Property
    -0.65
    Tu
    -0.65
    eret
    -0.64
    POSITIVE LOGITS
     cycle
    1.17
     campaign
    1.04
     season
    0.97
    stakes
    0.94
     campaigns
    0.89
     matchup
    0.87
    campaign
    0.85
     debates
    0.84
     trail
    0.84
     surge
    0.81
    Activations Density 0.101%

    No Known Activations