© 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. 1-RES-JB
    11. 20346
    Prev
    Next
    INDEX
    Explanations

    specific details and actions related to playing a card game

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with trading card games and their mechanics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accredited
    -0.77
     ACL
    -0.77
     Rodrig
    -0.73
    Þ
    -0.71
     eleph
    -0.70
    ¿½
    -0.69
     ape
    -0.69
     Pie
    -0.69
     Hue
    -0.67
     epile
    -0.66
    POSITIVE LOGITS
    Constructed
    0.94
     decks
    0.90
     deck
    0.85
     cards
    0.85
     mana
    0.83
    Spell
    0.83
    yard
    0.79
     card
    0.77
    caster
    0.77
     Spells
    0.76
    Activations Density 0.355%

    No Known Activations