© 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. 9-RES-JB
    11. 19806
    Prev
    Next
    INDEX
    Explanations

    locations or places where individuals come from

    oai_token-act-pair · gpt-3.5-turbo

    phrases that mention geographical origins or locations of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    faced
    -0.86
    ratulations
    -0.78
    few
    -0.77
    potion
    -0.73
    adata
    -0.69
    EPA
    -0.67
    assment
    -0.66
    rils
    -0.66
    attribute
    -0.65
     inval
    -0.65
    POSITIVE LOGITS
     afar
    1.37
     abroad
    1.04
     Latvia
    1.00
     Albania
    0.97
     Uganda
    0.96
     Nigeria
    0.96
     Finland
    0.95
     across
    0.94
     Denmark
    0.94
     Norway
    0.93
    Activations Density 0.102%

    No Known Activations