© 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. 15677
    Prev
    Next
    INDEX
    Explanations

    references to marriage or being married

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "married" and its variations, indicating relationship statuses

    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
     Flavoring
    -0.73
    otos
    -0.73
    ourse
    -0.71
    umbn
    -0.69
     millenn
    -0.68
    ostic
    -0.67
    vernment
    -0.67
    osure
    -0.66
    Platform
    -0.64
    acio
    -0.64
    POSITIVE LOGITS
     divorced
    0.99
     fiance
    0.91
     married
    0.89
    nesday
    0.87
    wife
    0.87
     marry
    0.87
     mistress
    0.85
    woman
    0.84
     cousin
    0.84
     wife
    0.83
    Activations Density 0.056%

    No Known Activations