© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 21362
    Prev
    Next
    INDEX
    Explanations

    mentions of or discussions related to women in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    topics related to women's representation and involvement in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ij士
    -0.80
    USS
    -0.76
    à¼
    -0.74
    ebus
    -0.71
    uin
    -0.71
    hiba
    -0.69
     Contents
    -0.68
    alion
    -0.68
    OUGH
    -0.66
     Tradable
    -0.65
    POSITIVE LOGITS
     breasts
    1.24
     childbirth
    1.16
     menstru
    1.13
     lesbian
    1.07
     husbands
    1.05
     bikini
    1.03
     empowerment
    1.03
     breastfeeding
    1.03
     pregnant
    1.01
     clitor
    1.01
    Activations Density 0.383%

    No Known Activations