© 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. 13884
    Prev
    Next
    INDEX
    Explanations

    words related to harbors, docks, and ports

    oai_token-act-pair · gpt-3.5-turbo

    references to locations related to water bodies and maritime activities

    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
    enhagen
    -0.75
    gee
    -0.74
    ivas
    -0.72
    iven
    -0.70
    olver
    -0.70
     Answer
    -0.69
     Matter
    -0.67
    letal
    -0.66
    hesis
    -0.65
    ioch
    -0.65
    POSITIVE LOGITS
    front
    1.07
    boats
    0.99
    boat
    0.94
     docks
    0.91
    yard
    0.88
     vessels
    0.81
     ports
    0.79
    yards
    0.78
     vessel
    0.77
     seas
    0.77
    Activations Density 0.057%

    No Known Activations