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

    Neuronpedia

    Jacobian LensNEW
    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. 16044
    Prev
    Next
    INDEX
    Explanations

    words related to specific groups of people, such as "People", "Men", and "Women"

    oai_token-act-pair · gpt-3.5-turbo

    references to different groups of people, specifically highlighting gender and identity

    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
     dads
    -0.69
    enegger
    -0.67
     husbands
    -0.64
     principals
    -0.64
     whipping
    -0.63
     fathers
    -0.62
     backbone
    -0.62
     parents
    -0.61
     stump
    -0.60
     pedoph
    -0.60
    POSITIVE LOGITS
    ysc
    0.82
    MpServer
    0.81
    ettlement
    0.77
     Eater
    0.75
    rights
    0.75
     Ago
    0.75
    ascript
    0.73
    Soft
    0.72
     Killed
    0.72
     Own
    0.72
    Activations Density 0.094%

    No Known Activations