© 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. 6577
    Prev
    Next
    INDEX
    Explanations

    information related to racial demographics, diversity, and ethnicity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to racial demographics and identity

    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
    forcement
    -0.86
    pmwiki
    -0.78
    odder
    -0.78
     defences
    -0.75
     deterrence
    -0.74
    NRS
    -0.72
    glers
    -0.70
    antics
    -0.70
     payoff
    -0.68
    Companies
    -0.68
    POSITIVE LOGITS
     Hispanic
    1.72
     Latino
    1.59
     Caucasian
    1.55
     Asian
    1.41
    Hispanic
    1.39
     African
    1.36
    Asian
    1.32
     Native
    1.28
     Filipino
    1.23
     Ethiopian
    1.22
    Activations Density 0.305%

    No Known Activations