© 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. 9-RES-JB
    11. 15650
    Prev
    Next
    INDEX
    Explanations

    phrases related to work equality, gender pay gap, salaries, and job roles

    oai_token-act-pair · gpt-3.5-turbo

    gender equality topics, particularly focusing on workforce disparities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.59
    ãĥ¯ãĥ³
    -0.56
    ËĪ
    -0.55
     Kislyak
    -0.52
    ãĥ¤
    -0.52
     "$
    -0.51
    ometimes
    -0.50
     Riders
    -0.49
     ):
    -0.49
    é¾
    -0.49
    POSITIVE LOGITS
     ..."
    2.00
    .")
    1.95
    )."
    1.89
     âĢ¦"
    1.82
    ."[
    1.79
    .'"
    1.78
    )"
    1.76
    '"
    1.74
    ,'"
    1.69
    ..."
    1.67
    Activations Density 2.907%

    No Known Activations