© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2273
    Prev
    Next
    INDEX
    Explanations

    the abbreviation "plebiscite" in the context of political discussions

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases related to political or election-related processes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     comparative
    -0.60
     Seasons
    -0.57
     Ingram
    -0.57
    ted
    -0.56
     Niet
    -0.55
     contender
    -0.54
     brid
    -0.54
     competitive
    -0.53
     TW
    -0.53
     Fighters
    -0.53
    POSITIVE LOGITS
    uits
    1.20
    ences
    1.16
    onduct
    1.13
    opes
    1.11
    uit
    1.06
    uity
    1.05
    ope
    1.05
    ussion
    1.04
    ounty
    1.02
    rimination
    1.02
    Activations Density 0.053%

    No Known Activations