© 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. 10-RES-JB
    11. 2891
    Prev
    Next
    INDEX
    Explanations

    gender-specific words related to roles of authority, particularly focusing on the presence of women in leadership positions

    oai_token-act-pair · gpt-3.5-turbo

    references to managers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    teenth
    -0.73
    DonaldTrump
    -0.69
    INGTON
    -0.68
    FER
    -0.67
    çīĪ
    -0.66
    SPONSORED
    -0.65
    READ
    -0.65
    ENC
    -0.64
    cale
    -0.62
    lihood
    -0.61
    POSITIVE LOGITS
    ial
    1.05
    ials
    0.93
    agers
    0.77
    iola
    0.76
    hips
    0.76
    icky
    0.76
    ubs
    0.75
    anova
    0.74
    ially
    0.73
    onym
    0.71
    Activations Density 0.042%

    No Known Activations