© 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. 18320
    Prev
    Next
    INDEX
    Explanations

    instances of bias or prejudice in text

    oai_token-act-pair · gpt-3.5-turbo

    references to bias and prejudice in various contexts

    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
    tons
    -0.74
    esc
    -0.72
    zech
    -0.70
    export
    -0.69
    sie
    -0.68
    loo
    -0.68
    phan
    -0.67
    akura
    -0.66
    Money
    -0.66
    URE
    -0.65
    POSITIVE LOGITS
     favoring
    1.09
    icial
    1.02
     towards
    1.01
     toward
    1.01
     bias
    0.92
     prejud
    0.91
     biases
    0.90
     against
    0.86
     detector
    0.83
     biased
    0.79
    Activations Density 0.042%

    No Known Activations