© 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. 3150
    Prev
    Next
    INDEX
    Explanations

    nautical terms and financial operations

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

    instances of foreign trade or shipping activities

    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
    emale
    -0.76
    nces
    -0.71
    bole
    -0.71
    gey
    -0.70
    natureconservancy
    -0.68
    ophobia
    -0.68
    ãĤ¦ãĤ¹
    -0.67
    ongevity
    -0.67
    ophob
    -0.66
     FACE
    -0.66
    POSITIVE LOGITS
     shipment
    1.92
     shipments
    1.79
     cargo
    1.77
     warehouses
    1.58
     shipping
    1.54
     freight
    1.50
     shipped
    1.48
     containers
    1.47
     unloaded
    1.45
     transporting
    1.45
    Activations Density 0.670%

    No Known Activations