© 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. 13288
    Prev
    Next
    INDEX
    Explanations

    phrases related to military personnel and operations, especially regarding gender transitions and military regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to military service and transgender issues

    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
    jab
    -0.88
    Torrent
    -0.83
    thereum
    -0.77
     Lovecraft
    -0.76
    iPhone
    -0.75
    Block
    -0.75
    odynamic
    -0.74
    conom
    -0.73
     Dracula
    -0.72
    Meta
    -0.71
    POSITIVE LOGITS
     Soldiers
    1.86
     soldiers
    1.85
    Army
    1.84
     soldier
    1.81
    Military
    1.80
     Army
    1.78
     Marines
    1.77
     Military
    1.70
     military
    1.70
     Infantry
    1.69
    Activations Density 1.047%

    No Known Activations