© 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. 6-RES-JB
    11. 13465
    Prev
    Next
    INDEX
    Explanations

    keywords related to a specific strategy or game in the context of gaming, likely related to card games or board games

    oai_token-act-pair · gpt-3.5-turbo

    elements related to 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 @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HIP
    -0.92
     Philips
    -0.71
     commencement
    -0.68
     Sirius
    -0.67
    asonic
    -0.65
     Mens
    -0.65
     HIT
    -0.64
     Rodrig
    -0.64
     GPS
    -0.63
     Mig
    -0.63
    POSITIVE LOGITS
     mana
    1.01
     decks
    0.98
     cards
    0.96
    magic
    0.87
     orcs
    0.86
     Spells
    0.84
    Spell
    0.83
    caster
    0.83
     Cards
    0.83
     Hearthstone
    0.83
    Activations Density 0.116%

    No Known Activations