© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 2851
    Prev
    Next
    INDEX
    Explanations

    demographic information such as nationality, age, and ethnicity

    oai_token-act-pair · gpt-3.5-turbo

    subjects related to demographic categories and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ciation
    -0.87
    forcement
    -0.87
    illance
    -0.83
    ð
    -0.77
    olon
    -0.73
    vironment
    -0.72
    idation
    -0.72
    lag
    -0.71
    opolis
    -0.70
    daq
    -0.70
    POSITIVE LOGITS
     teenagers
    1.15
     retirees
    1.14
     foreigners
    1.06
     graduates
    1.06
     natives
    1.05
     males
    1.03
     orphans
    1.02
     civilians
    1.02
     Saudis
    1.01
     volunteers
    1.01
    Activations Density 0.243%

    No Known Activations