© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8547
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical regions or nationalities, especially focusing on Asian countries

    oai_token-act-pair · gpt-3.5-turbo

    references to "Asian" as a descriptor in various contexts

    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
    vous
    -0.89
    Ö¼
    -0.87
    umbnails
    -0.83
    */(
    -0.83
    ainer
    -0.80
    lement
    -0.79
    ochet
    -0.78
    DCS
    -0.78
    odder
    -0.76
    yard
    -0.75
    POSITIVE LOGITS
    Asian
    1.10
     Asian
    1.09
     Minor
    0.88
     Asians
    0.88
     ethnicity
    0.86
     carp
    0.81
     nationals
    0.81
    ethnic
    0.79
     immigrant
    0.79
     Pacific
    0.79
    Activations Density 0.007%

    No Known Activations