© 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. 0-RES-JB
    11. 19074
    Prev
    Next
    INDEX
    Explanations

    words related to African countries or people

    oai_token-act-pair · gpt-3.5-turbo

    references to Africa, its culture, and its people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scroll
    -0.66
    ogle
    -0.66
    rings
    -0.65
     sacrament
    -0.64
    Thumbnail
    -0.64
    sels
    -0.62
    ortion
    -0.61
     pizza
    -0.61
    null
    -0.60
    âĸĪâĸĪ
    -0.60
    POSITIVE LOGITS
     Af
    4.06
    Af
    2.32
     Afric
    1.63
     af
    1.45
     Afgh
    1.43
     Ethiop
    1.28
     Ethiopian
    1.24
     AF
    1.21
     African
    1.19
     Africans
    1.16
    Activations Density 0.016%

    No Known Activations