© 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. 1428
    Prev
    Next
    INDEX
    Explanations

    phrases related to diplomatic relations and ambassadors

    oai_token-act-pair · gpt-3.5-turbo

    references to diplomatic roles and positions related to ambassadors

    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
     coaster
    -0.80
     herd
    -0.68
     autop
    -0.66
     treadmill
    -0.66
     mills
    -0.65
     thrill
    -0.64
     nets
    -0.64
     loads
    -0.62
     strips
    -0.62
     accum
    -0.60
    POSITIVE LOGITS
     Libya
    1.11
     Uzbek
    1.11
     Ankara
    1.08
     NATO
    1.06
     UNESCO
    1.04
    uador
    1.04
     Geneva
    1.01
     Syria
    0.99
     Nato
    0.97
     Ukraine
    0.96
    Activations Density 0.072%

    No Known Activations