© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 5021
    Prev
    Next
    INDEX
    Explanations

    phrases related to political tensions between countries

    oai_token-act-pair · gpt-3.5-turbo

    references to rising tensions or conflicts between countries or regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mercy
    -0.70
    icle
    -0.65
    missions
    -0.63
     slideshow
    -0.62
     cures
    -0.62
     miracle
    -0.61
    ostics
    -0.60
    leton
    -0.59
     selects
    -0.59
    icles
    -0.58
    POSITIVE LOGITS
     tensions
    1.21
     between
    1.16
     flared
    1.14
     flare
    1.09
     simmer
    1.08
    between
    1.07
     tension
    1.04
     heightened
    1.01
     strained
    1.01
    escal
    0.94
    Activations Density 0.100%

    No Known Activations