© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12876
    Prev
    Next
    INDEX
    Explanations

    characteristics related to identity and discrimination, such as sexual orientation, gender identity, race, nationality, religion, disability, and age

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sexual orientation and gender identity

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ERG
    -0.91
    AMS
    -0.75
    awar
    -0.71
    okin
    -0.66
    erg
    -0.66
    pload
    -0.64
    usable
    -0.63
    ugal
    -0.62
     besieged
    -0.62
    assic
    -0.61
    POSITIVE LOGITS
     ancestry
    0.92
     affiliation
    0.90
     preferences
    0.86
     backgrounds
    0.84
     affili
    0.82
     ancest
    0.81
     origin
    0.81
     surname
    0.81
     background
    0.77
     spectrum
    0.76
    Activations Density 0.169%

    No Known Activations