© 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. 1-RES-JB
    11. 20927
    Prev
    Next
    INDEX
    Explanations

    words related to intolerance or insensitivity

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with intolerance and insensitivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pool
    -0.83
    uld
    -0.78
    ramid
    -0.76
    lished
    -0.75
     Skydragon
    -0.75
    #$#$
    -0.74
    ynthesis
    -0.72
     Pool
    -0.70
     Eternity
    -0.68
     Vapor
    -0.68
    POSITIVE LOGITS
     intoler
    1.38
     intolerance
    1.36
     tolerant
    1.01
     insensitive
    0.97
     prejud
    0.85
     prejudice
    0.85
     homophobic
    0.82
     sexist
    0.79
     racists
    0.78
     caric
    0.77
    Activations Density 0.013%

    No Known Activations