© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 17270
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations, especially place names

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific geopolitical region or related issues

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Jaguar
    -0.65
    rim
    -0.60
     Drift
    -0.59
    Hug
    -0.59
     Keys
    -0.58
    Assembly
    -0.57
     Arab
    -0.57
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.57
    ré
    -0.56
    VW
    -0.56
    POSITIVE LOGITS
    hift
    1.08
    terday
    1.06
    sembly
    0.98
    ettings
    0.97
    leep
    0.94
    etheless
    0.93
    theless
    0.92
    cius
    0.92
    cript
    0.87
    uggest
    0.87
    Activations Density 0.022%

    No Known Activations