Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 15190
    Prev
    Next
    INDEX
    Explanations

    mention a predominantly Asian ethnic group

    oai_token-act-pair · gpt-3.5-turbo

    references to Asian representation in media and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     caches
    -0.78
    forcement
    -0.78
    Synopsis
    -0.73
     deterrence
    -0.73
     generators
    -0.71
     checkpoints
    -0.71
     payoff
    -0.70
     inspections
    -0.70
     aval
    -0.69
    Reviewer
    -0.68
    POSITIVE LOGITS
     Hispanic
    1.78
     Caucasian
    1.72
     Latino
    1.58
    Hispanic
    1.50
    Asian
    1.48
     Asian
    1.45
     Asians
    1.39
    aucas
    1.36
     African
    1.33
     Hispanics
    1.32
    Activations Density 0.449%

    No Known Activations