© 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. 10-RES-JB
    11. 20679
    Prev
    Next
    INDEX
    Explanations

    countries, political figures, and government-related terms

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to geopolitical issues and countries

    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
    mble
    -0.62
     Niet
    -0.61
    indu
    -0.52
     Hiroshima
    -0.50
    yip
    -0.49
    RW
    -0.49
    pires
    -0.47
    }"
    -0.46
    veyard
    -0.46
    tumblr
    -0.46
    POSITIVE LOGITS
    's
    0.95
     coffers
    0.68
    ÃŃs
    0.65
     because
    0.59
     amid
    0.58
     whereby
    0.57
    Care
    0.56
     throughout
    0.56
     through
    0.54
     lately
    0.54
    Activations Density 0.471%

    No Known Activations