© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11-RES-JB
    11. 9511
    Prev
    Next
    INDEX
    Explanations

    phrases related to social issues, especially outdated social norms and gender biases

    oai_token-act-pair · gpt-3.5-turbo

    references to societal norms and the effects of gender bias

    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
    endment
    -0.87
    etsk
    -0.84
    ospons
    -0.83
    hire
    -0.81
    amen
    -0.79
    ppa
    -0.76
    osponsors
    -0.73
    hots
    -0.72
     Schn
    -0.72
    earch
    -0.71
    POSITIVE LOGITS
     stereotypes
    1.74
     prejudices
    1.67
     notions
    1.66
     precon
    1.65
     assumptions
    1.61
     norms
    1.49
     stereotype
    1.47
     beliefs
    1.45
     biases
    1.40
     myths
    1.39
    Activations Density 0.408%

    No Known Activations