© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 13158
    Prev
    Next
    INDEX
    Explanations

    information related to character abilities in a video game

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.15
    2:0.04
    3:0.05
    4:0.03
    5:0.05
    6:0.07
    7:0.13
    8:0.04
    9:0.08
    10:0.17
    11:0.09
    Negative Logits
     UNCLASSIFIED
    -1.81
    terday
    -1.73
     politic
    -1.56
     photographed
    -1.53
     advoc
    -1.53
    eteenth
    -1.52
    ovie
    -1.49
     videot
    -1.47
     horizont
    -1.45
     enthusi
    -1.45
    POSITIVE LOGITS
     cooldown
    2.14
     Melee
    2.13
     mage
    1.98
     Enchant
    1.95
     rune
    1.92
     melee
    1.89
     enchantment
    1.87
     spells
    1.87
    Spell
    1.87
     Enemies
    1.86
    Activations Density 0.325%

    No Known Activations