© 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. 7763
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "marriage" and related terms like "marriage ceremonies," "marriage rights," and "marriage equality."

    oai_token-act-pair · gpt-3.5-turbo
    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
    atche
    -0.77
    selves
    -0.68
     Runner
    -0.68
     Chocobo
    -0.67
    OLOG
    -0.66
    ocl
    -0.66
     Logged
    -0.65
    ergic
    -0.63
    é¾
    -0.62
    asel
    -0.62
    POSITIVE LOGITS
     equality
    1.45
    equality
    1.12
     Equality
    1.09
     vows
    1.05
    riages
    1.02
     ceremonies
    0.97
     ceremony
    0.94
     licenses
    0.92
     couples
    0.90
     counseling
    0.89
    Activations Density 0.073%

    No Known Activations