© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 16320
    Prev
    Next
    INDEX
    Explanations

    mentions of laws or political discussions related to same-sex marriage

    oai_token-act-pair · gpt-3.5-turbo

    references to same-sex relationships and marriage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     notebooks
    -0.67
     forecast
    -0.66
     reserves
    -0.65
     aluminum
    -0.64
     Fract
    -0.62
     Mob
    -0.62
     Glacier
    -0.61
     notebook
    -0.61
     iceberg
    -0.61
     KP
    -0.60
    POSITIVE LOGITS
    sex
    4.37
    Sex
    2.41
    sexual
    2.15
    gender
    1.94
     sex
    1.91
     Sex
    1.89
    Sexual
    1.79
    Gender
    1.69
     sexes
    1.48
     Sexual
    1.44
    Activations Density 0.015%

    No Known Activations