© 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 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. 13577
    Prev
    Next
    INDEX
    Explanations

    phrases related to port cities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific port locations and their associations

    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
    schild
    -0.73
    feld
    -0.69
    fy
    -0.66
    kai
    -0.66
    meyer
    -0.65
     Ernst
    -0.64
    natureconservancy
    -0.64
    enhagen
    -0.63
     leukemia
    -0.63
    sect
    -0.61
    POSITIVE LOGITS
    uese
    1.17
    ão
    0.89
    ante
    0.70
     Rican
    0.69
    PORT
    0.69
    ón
    0.68
    sylvania
    0.67
    lished
    0.66
     Calais
    0.64
    oit
    0.63
    Activations Density 0.086%

    No Known Activations