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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3585
    Prev
    Next
    INDEX
    Explanations

    mentions of same-sex marriage

    oai_token-act-pair · gpt-3.5-turbo

    references 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 @ 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
     Tiff
    -0.77
     almonds
    -0.70
     Tens
    -0.67
     brim
    -0.66
     Duff
    -0.65
     Mog
    -0.65
    zsche
    -0.63
     HUN
    -0.63
     prematurely
    -0.62
     Anth
    -0.61
    POSITIVE LOGITS
    sex
    1.84
    gender
    1.49
    Sex
    1.35
    origin
    1.30
    race
    1.26
    species
    1.21
    same
    1.12
    racial
    1.09
    marriage
    1.08
    day
    1.08
    Activations Density 0.016%

    No Known Activations