© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 14037
    Prev
    Next
    INDEX
    Explanations

    phrases related to military actions and conflict

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events and actions related to conflict and war

    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
    velop
    -0.89
    byss
    -0.86
    earchers
    -0.83
    ezvous
    -0.81
     glim
    -0.78
    reau
    -0.77
    ients
    -0.75
    knit
    -0.73
    mith
    -0.70
    itures
    -0.69
    POSITIVE LOGITS
     imperialist
    1.45
     NATO
    1.39
     Gaddafi
    1.39
     dictators
    1.35
     fascist
    1.34
     Erdogan
    1.31
     Saddam
    1.29
     Putin
    1.28
     Bashar
    1.26
     imperialism
    1.25
    Activations Density 0.685%

    No Known Activations