© 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. 11641
    Prev
    Next
    INDEX
    Explanations

    words related to myths, misconceptions, and stereotypes

    oai_token-act-pair · gpt-3.5-turbo

    references to myths and misconceptions, particularly those related to stereotypes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    misconceptions

    Explanation Uploaded by User
    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
    •henryjames
    how did the passage get overloaded with this?

    No Comments

    Negative Logits
    Interstitial
    -0.72
    anmar
    -0.67
    maxwell
    -0.65
    ptroller
    -0.64
    issions
    -0.64
    berus
    -0.63
    ieri
    -0.63
    CLASSIFIED
    -0.62
     agre
    -0.62
    TPP
    -0.62
    POSITIVE LOGITS
     about
    1.64
     ABOUT
    1.48
    about
    1.26
     About
    1.25
     regarding
    1.22
     concerning
    1.18
     surrounding
    1.04
    About
    0.93
     pertaining
    0.89
     ingrained
    0.89
    Activations Density 0.238%

    No Known Activations