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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7258
    Prev
    Next
    INDEX
    Explanations

    phrases related to motherhood

    oai_token-act-pair · gpt-3.5-turbo

    mentions of mothers and their roles

    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
     Artifact
    -0.66
     Barbarian
    -0.64
    con
    -0.63
    lite
    -0.62
     wizard
    -0.61
     Sphere
    -0.60
     cog
    -0.60
    edit
    -0.60
    bender
    -0.60
    ernaut
    -0.59
    POSITIVE LOGITS
     mothers
    3.34
     moms
    2.91
     Mothers
    2.68
     dads
    2.43
     fathers
    2.40
     husbands
    2.16
     wives
    1.87
     babies
    1.72
     parents
    1.72
     infants
    1.69
    Activations Density 0.016%

    No Known Activations