© 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. 8-RES-JB
    11. 22400
    Prev
    Next
    INDEX
    Explanations

    mentions related to the concept of "white" in a social or political context

    oai_token-act-pair · gpt-3.5-turbo

    references to race, specifically focusing on the concept of "white."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yrinth
    -1.01
    cffffcc
    -0.93
    ategory
    -0.78
    ysis
    -0.76
    gd
    -0.76
    alg
    -0.76
    HCR
    -0.76
    interstitial
    -0.76
    rocal
    -0.74
    Sym
    -0.74
    POSITIVE LOGITS
     supremacist
    1.48
     supremacists
    1.33
     supremacy
    1.21
     nationalist
    1.10
    beard
    0.99
    bread
    0.97
     suprem
    0.95
     nationalists
    0.93
     males
    0.85
    face
    0.84
    Activations Density 0.036%

    No Known Activations