© 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. 3322
    Prev
    Next
    INDEX
    Explanations

    statements related to unequal treatment based on race, gender, or sexual orientation

    oai_token-act-pair · gpt-3.5-turbo

    references to discrimination and unfair treatment of marginalized groups

    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
    pex
    -0.69
     Knot
    -0.68
     helium
    -0.67
     leak
    -0.61
     Sync
    -0.61
     ellipt
    -0.60
     bluff
    -0.60
     logo
    -0.59
     Oper
    -0.58
     Tycoon
    -0.57
    POSITIVE LOGITS
     discrimination
    0.98
    ardless
    0.95
    reatment
    0.94
     discriminated
    0.90
     due
    0.89
     unfairly
    0.85
     afforded
    0.84
     academ
    0.83
     unjust
    0.82
     irrespective
    0.82
    Activations Density 0.322%

    No Known Activations