© 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. 2297
    Prev
    Next
    INDEX
    Explanations

    references related to military service and tributes to soldiers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of military service and veterans

    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
     Gould
    -0.75
    sche
    -0.74
     DJs
    -0.71
    ãĤ¦ãĤ¹
    -0.71
     dop
    -0.70
    Owner
    -0.69
     kW
    -0.68
     Rowling
    -0.67
    Electric
    -0.67
    ellar
    -0.67
    POSITIVE LOGITS
     combat
    1.46
     battlefield
    1.38
     infantry
    1.38
     soldiers
    1.36
     Infantry
    1.34
    combat
    1.34
     soldier
    1.32
     WWII
    1.31
     military
    1.30
    geant
    1.29
    Activations Density 0.598%

    No Known Activations