© 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. 23079
    Prev
    Next
    INDEX
    Explanations

    words related to differences and similarities among people, including their backgrounds, values, and cultures

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to cultural and social diversity

    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
    swer
    -0.85
    pless
    -0.83
    ''''
    -0.76
    maxwell
    -0.75
    iatus
    -0.73
    Ĥİ
    -0.73
    scrib
    -0.72
    chester
    -0.70
    Row
    -0.70
    vation
    -0.69
    POSITIVE LOGITS
     lifestyles
    1.49
     worldview
    1.45
     customs
    1.43
     traditions
    1.43
     beliefs
    1.41
     philosophies
    1.39
     motivations
    1.34
     histories
    1.34
     cultures
    1.34
     sensibilities
    1.34
    Activations Density 0.233%

    No Known Activations