© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14356
    Prev
    Next
    INDEX
    Explanations

    references to special energy mechanics within a game context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.05
    2:0.15
    3:0.07
    4:0.14
    5:0.04
    6:0.09
    7:0.07
    8:0.04
    9:0.06
    10:0.06
    11:0.10
    Negative Logits
    田
    -2.85
    之
    -2.63
    �
    -2.43
    ة
    -2.38
     Johns
    -2.34
    apixel
    -2.33
    ¨
    -2.30
    ometer
    -2.24
     advoc
    -2.24
    uala
    -2.23
    POSITIVE LOGITS
     aggro
    3.71
     cards
    3.69
     card
    3.30
     decks
    3.25
     mana
    3.14
     discard
    3.13
     creatures
    3.09
     Pyro
    3.06
     counters
    3.06
     Jace
    3.04
    Activations Density 0.170%

    No Known Activations