© 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. 11-RES-JB
    11. 13492
    Prev
    Next
    INDEX
    Explanations

    mentions or references to a specific magazine named "LIFE"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media and news outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    åī
    -0.77
    uesday
    -0.74
     Hatt
    -0.70
    ãĥķãĤ©
    -0.69
     Taj
    -0.68
    cz
    -0.68
    handler
    -0.67
     tart
    -0.66
     Patterson
    -0.65
    terson
    -0.65
    POSITIVE LOGITS
     Life
    1.98
     life
    1.88
    Life
    1.84
     LIFE
    1.82
    life
    1.76
    live
    1.73
     Live
    1.71
    Live
    1.71
     live
    1.70
     Living
    1.62
    Activations Density 0.263%

    No Known Activations