© 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. 11149
    Prev
    Next
    INDEX
    Explanations

    mentions of spouses or partners in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    references to husbands and wives

    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
    rawdownloadcloneembedreportprint
    -0.71
    WAY
    -0.71
    pmwiki
    -0.69
     Ukrain
    -0.69
     Flavoring
    -0.66
    wcs
    -0.65
     Races
    -0.65
    Materials
    -0.63
    osta
    -0.62
    UGE
    -0.62
    POSITIVE LOGITS
    husband
    0.90
    hood
    0.81
    wife
    0.76
    doctor
    0.74
    DOM
    0.74
    shake
    0.74
    ry
    0.74
    men
    0.73
    nesday
    0.72
    bug
    0.72
    Activations Density 0.041%

    No Known Activations