© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 12088
    Prev
    Next
    INDEX
    Explanations

    words related to countries and specific locations

    oai_token-act-pair · gpt-3.5-turbo

    names of countries, particularly in relation to serious events or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    earable
    -0.89
    idth
    -0.79
    ellation
    -0.79
     accur
    -0.78
    alty
    -0.78
     bets
    -0.76
    ancies
    -0.76
    itbart
    -0.76
    aturdays
    -0.75
    utherland
    -0.74
    POSITIVE LOGITS
     Congo
    1.10
     Erit
    0.93
     Leone
    0.91
     Cameroon
    0.90
     Africa
    0.88
     Angola
    0.88
     Laos
    0.87
     Liberia
    0.87
     Albania
    0.86
     Basin
    0.85
    Activations Density 0.059%

    No Known Activations