© 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. 7-RES-JB
    11. 22951
    Prev
    Next
    INDEX
    Explanations

    details related to military units and operations

    oai_token-act-pair · gpt-3.5-turbo

    military ranks and units

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Blockchain
    -0.92
     Patreon
    -0.90
     Ethereum
    -0.90
     Spotify
    -0.87
    geist
    -0.87
    Bitcoin
    -0.86
     Airbnb
    -0.86
     Wallet
    -0.83
     Rowling
    -0.83
     Kanye
    -0.82
    POSITIVE LOGITS
     civilian
    1.41
     reconnaissance
    1.40
     Aircraft
    1.38
     infantry
    1.34
     USAF
    1.32
     aircraft
    1.32
     munitions
    1.31
    ircraft
    1.28
     Marines
    1.28
     marines
    1.27
    Activations Density 1.119%

    No Known Activations