© 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. 8-RES-JB
    11. 19340
    Prev
    Next
    INDEX
    Explanations

    terms related to Zen

    oai_token-act-pair · gpt-3.5-turbo

    references to "Zen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lauder
    -0.70
     mileage
    -0.67
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.64
    riers
    -0.63
     encour
    -0.61
     Md
    -0.60
     Tolkien
    -0.59
     Mississ
    -0.59
    IRD
    -0.58
     Mulcair
    -0.58
    POSITIVE LOGITS
    obia
    1.16
    eca
    1.16
    ith
    0.99
    itized
    0.98
    zen
    0.92
    ical
    0.90
    arist
    0.90
    geist
    0.90
    ica
    0.88
    emy
    0.87
    Activations Density 0.036%

    No Known Activations