© 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. 10-RES-JB
    11. 2927
    Prev
    Next
    INDEX
    Explanations

    references to same-sex relationships or marriage

    oai_token-act-pair · gpt-3.5-turbo

    terms related to same-sex marriage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    efficiency
    -0.74
    Dispatch
    -0.73
    assic
    -0.72
    unker
    -0.72
    unes
    -0.71
    Nap
    -0.71
    thin
    -0.67
    OUGH
    -0.67
    PsyNetMessage
    -0.67
     Manufacturer
    -0.66
    POSITIVE LOGITS
     marriage
    1.46
     couples
    1.43
     marriages
    1.43
    marriage
    1.30
     spouses
    1.21
     Marriage
    1.15
     weddings
    1.13
     married
    1.09
     marry
    1.05
     spouse
    0.99
    Activations Density 0.040%

    No Known Activations