© 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. 9-RES-JB
    11. 15574
    Prev
    Next
    INDEX
    Explanations

    mentions of countries in the context of political or military activities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific countries, particularly China, Russia, Israel, North Korea, and Turkey

    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
    soDeliveryDate
    -0.81
    ocamp
    -0.75
    ãĤ¦ãĤ¹
    -0.72
    veyard
    -0.72
    notation
    -0.68
    ivery
    -0.67
     Grail
    -0.66
    tml
    -0.64
    SpaceEngineers
    -0.63
    geries
    -0.63
    POSITIVE LOGITS
     accuses
    1.05
     considers
    1.02
     reacted
    0.99
     retali
    0.99
     denies
    0.98
     withdrew
    0.98
     blames
    0.96
     intends
    0.95
     responded
    0.94
     has
    0.93
    Activations Density 0.160%

    No Known Activations