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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2-RES-JB
    11. 12610
    Prev
    Next
    INDEX
    Explanations

    statements containing the word "feminist" with varying degrees of relevance and emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to feminism and feminists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sight
    -0.82
    laus
    -0.80
    INESS
    -0.74
    seeing
    -0.72
    mg
    -0.71
    acca
    -0.70
    gob
    -0.69
    Condition
    -0.69
    rip
    -0.68
    shape
    -0.68
    POSITIVE LOGITS
     feminists
    1.01
     feminist
    0.96
     feminism
    0.95
    galitarian
    0.85
     Feminist
    0.83
    azi
    0.80
     Equality
    0.71
     tracts
    0.71
     empowerment
    0.71
    andom
    0.70
    Activations Density 0.016%

    No Known Activations