© 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. 17498
    Prev
    Next
    INDEX
    Explanations

    phrases related to political campaigns

    oai_token-act-pair · gpt-3.5-turbo

    significant political topics and controversies related to campaigns

    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
     TTL
    -0.79
     âĸĪ
    -0.78
     Mages
    -0.77
     UNIVERS
    -0.76
     Godd
    -0.74
     Engineers
    -0.73
     !!
    -0.72
    aea
    -0.71
     ORDER
    -0.71
     Wikimedia
    -0.71
    POSITIVE LOGITS
     speeches
    1.23
     rhetoric
    1.20
     stances
    1.11
     stump
    1.10
     themes
    1.07
     surrog
    1.06
     railing
    1.06
     critiques
    1.05
     campaigning
    1.02
     spar
    1.01
    Activations Density 0.613%

    No Known Activations