© 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. 1-RES-JB
    11. 4869
    Prev
    Next
    INDEX
    Explanations

    terms related to gender discrimination and bias, particularly focusing on sexism

    oai_token-act-pair · gpt-3.5-turbo

    references to sexism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyde
    -0.82
    Trust
    -0.76
    Route
    -0.74
    ________________________
    -0.70
    mental
    -0.69
    fee
    -0.68
    Reviewer
    -0.68
    ving
    -0.66
    uilding
    -0.65
    manuel
    -0.65
    POSITIVE LOGITS
     sexist
    1.17
     sexism
    0.97
     misogyn
    0.85
     banter
    0.82
     stereotypes
    0.80
    endered
    0.77
     stereotyp
    0.77
    inem
    0.76
     gender
    0.75
     Equality
    0.75
    Activations Density 0.012%

    No Known Activations