© 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. 8-RES-JB
    11. 17774
    Prev
    Next
    INDEX
    Explanations

    information regarding marriages

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "married" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.98
    nesota
    -0.77
    olin
    -0.77
    urg
    -0.75
    vernment
    -0.73
    abwe
    -0.73
    ostic
    -0.72
    atics
    -0.72
    affer
    -0.70
    opia
    -0.69
    POSITIVE LOGITS
    nesday
    0.99
     married
    0.82
    ton
    0.77
     marry
    0.77
     divorced
    0.75
     couples
    0.73
    married
    0.70
    equality
    0.70
     marrying
    0.70
     divorce
    0.70
    Activations Density 0.038%

    No Known Activations