© 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. 12-RES-JB
    11. 4047
    Prev
    Next
    INDEX
    Explanations

    information related to sailors, sailing, and nautical terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to superstition and nautical traditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Nuggets
    -0.85
    Denver
    -0.80
    ÅŁ
    -0.75
    à¦
    -0.74
     Peyton
    -0.72
     UD
    -0.71
     CPS
    -0.71
    ©¶æ
    -0.71
     Rahul
    -0.71
     McGee
    -0.70
    POSITIVE LOGITS
     maritime
    2.18
     sailors
    2.12
     Maritime
    2.07
     sailing
    2.07
     seaf
    2.04
     sail
    2.04
     sailor
    2.01
     naval
    1.99
     ships
    1.98
     ship
    1.96
    Activations Density 1.340%

    No Known Activations