© 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. 2-RES-JB
    11. 795
    Prev
    Next
    INDEX
    Explanations

    the word "gender"

    oai_token-act-pair · gpt-4-turbo

    words related to gender

    oai_token-act-pair · gpt-3.5-turbo

    references to gender issues and equality

    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
    etsk
    -0.68
    ernels
    -0.68
    steen
    -0.67
     Memor
    -0.66
     GOODMAN
    -0.65
    amina
    -0.65
    iries
    -0.63
    66666666
    -0.63
    ournal
    -0.63
    ×Ļ×
    -0.63
    POSITIVE LOGITS
     dysph
    0.98
    endered
    0.98
     genders
    0.91
     gender
    0.91
     equality
    0.87
    fuck
    0.82
     infertility
    0.82
     stereotypes
    0.82
     pronouns
    0.81
     Equality
    0.81
    Activations Density 0.014%

    No Known Activations