Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 717
    Prev
    Next
    INDEX
    Explanations

    spousal relationships and mentions of spouses

    oai_token-act-pair · gpt-3.5-turbo

    references to spouses and marital relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĢ
    -0.73
    imet
    -0.70
     Kard
    -0.65
    jab
    -0.64
    cart
    -0.64
    slow
    -0.64
     Sam
    -0.64
    Dem
    -0.64
     slack
    -0.64
     Moor
    -0.63
    POSITIVE LOGITS
     spouses
    3.40
     spouse
    3.33
     husbands
    1.70
     marital
    1.55
     wives
    1.53
     retirees
    1.31
     marriages
    1.30
     caregivers
    1.21
    married
    1.19
     heirs
    1.16
    Activations Density 0.023%

    No Known Activations