© 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. 11246
    Prev
    Next
    INDEX
    Explanations

    phrases related to marriage or relationships

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to marital relationships and partnerships

    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
    wcs
    -0.86
    mort
    -0.72
     empt
    -0.71
    inventory
    -0.70
    pmwiki
    -0.69
     audits
    -0.66
    staking
    -0.65
     atmosp
    -0.64
     redes
    -0.64
     calibration
    -0.63
    POSITIVE LOGITS
     prostitute
    1.07
     actress
    0.98
     classmate
    0.95
     prostitutes
    0.94
     boyfriend
    0.93
     someone
    0.92
     her
    0.89
     whom
    0.88
     girlfriend
    0.88
     mistress
    0.88
    Activations Density 0.179%

    No Known Activations