© 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. 2-RES-JB
    11. 12466
    Prev
    Next
    INDEX
    Explanations

    keywords related to reality TV show "Real Housewives" and the concept of being a housewife

    oai_token-act-pair · gpt-3.5-turbo

    references to "wives" and "wives" related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orescent
    -0.75
     constitu
    -0.71
     contagious
    -0.71
     blocking
    -0.70
     distinguishing
    -0.69
     shielding
    -0.68
    ucket
    -0.68
    psey
    -0.68
    encing
    -0.65
     hypers
    -0.64
    POSITIVE LOGITS
    wife
    1.08
    hood
    0.98
    wives
    0.98
    ciation
    0.88
    theless
    0.85
    doctor
    0.82
    apy
    0.81
    glers
    0.80
    xy
    0.77
    cible
    0.77
    Activations Density 0.012%

    No Known Activations