© 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. 18707
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations, specifically focused on continents, countries, and regions

    oai_token-act-pair · gpt-3.5-turbo

    references to continental regions or geographic entities related to the United States

    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
    HUD
    -0.87
    externalActionCode
    -0.76
    atta
    -0.74
    oku
    -0.72
    oun
    -0.71
    CHAT
    -0.71
    tu
    -0.71
    HCR
    -0.70
    acl
    -0.69
    nir
    -0.69
    POSITIVE LOGITS
     shelf
    0.94
     shelves
    0.88
     STATES
    0.87
    continental
    0.85
     continents
    0.85
     drift
    0.84
     continental
    0.84
     Continent
    0.84
     Europe
    0.83
     Europeans
    0.83
    Activations Density 0.042%

    No Known Activations