© 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. 0-RES-JB
    11. 9687
    Prev
    Next
    INDEX
    Explanations

    the name "Luck"

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent sports figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     butterfly
    -0.73
    oat
    -0.71
     pneum
    -0.70
     compos
    -0.70
     crab
    -0.68
     arch
    -0.66
     composer
    -0.66
     pod
    -0.63
     stale
    -0.63
     fork
    -0.62
    POSITIVE LOGITS
     Luck
    2.61
     Dak
    2.33
     Agu
    1.68
    Luck
    1.60
     Og
    1.03
     Armour
    0.99
     Zak
    0.97
     Andrews
    0.95
     Uttar
    0.94
     Baylor
    0.90
    Activations Density 0.015%

    No Known Activations