© 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. 20736
    Prev
    Next
    INDEX
    Explanations

    phrases related to discrimination and bias based on various characteristics such as race, gender, sexual orientation, and nationality

    oai_token-act-pair · gpt-3.5-turbo

    references to discrimination based on various characteristics such as race, sexual orientation, or disability

    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
    eva
    -0.82
    iland
    -0.77
    jet
    -0.75
    cca
    -0.69
    Guard
    -0.67
    MO
    -0.66
    adia
    -0.65
    cember
    -0.64
    NAS
    -0.64
    jan
    -0.64
    POSITIVE LOGITS
     ethnicity
    1.24
     nationality
    1.18
     merit
    1.13
     whether
    1.07
     race
    1.05
     gender
    1.04
     characteristics
    1.03
     geography
    1.02
     demographics
    1.01
     similarity
    1.00
    Activations Density 0.245%

    No Known Activations