© 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. 2-RES-JB
    11. 12986
    Prev
    Next
    INDEX
    Explanations

    the word "multicultural" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to multiculturalism and cultural diversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulz
    -0.81
    IELD
    -0.78
    INESS
    -0.77
    HOME
    -0.76
    ACH
    -0.76
    Medic
    -0.74
    yer
    -0.74
    attr
    -0.73
    uden
    -0.72
    orah
    -0.72
    POSITIVE LOGITS
    ism
    1.23
     bilingual
    0.99
    icultural
    0.98
     multicultural
    0.98
    isms
    0.97
    ilingual
    0.91
    icol
    0.87
    istani
    0.86
    inational
    0.80
     separat
    0.79
    Activations Density 0.012%

    No Known Activations