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. 8-RES-JB
    6. 8739
    Prev
    Next
    INDEX
    Explanations

    mentions of women, children, and family members in contexts that may involve distressing or harmful situations

    oai_token-act-pair · gpt-3.5-turbo

    references to women and children in contexts of social issues or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prol
    -0.75
     Hoover
    -0.71
    RP
    -0.66
    ommel
    -0.66
     Pradesh
    -0.63
     Tough
    -0.61
    eon
    -0.61
    Wan
    -0.61
     Kinnikuman
    -0.60
     Collider
    -0.60
    POSITIVE LOGITS
     minorities
    1.04
     children
    1.02
     infants
    0.93
     girls
    0.92
     skirts
    0.88
     breasts
    0.88
     unborn
    0.88
     childbirth
    0.86
     babies
    0.84
    girls
    0.83
    Activations Density 0.184%

    No Known Activations