© 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. 10-ATT-KK
    11. 16403
    Prev
    Next
    INDEX
    Explanations

    mentions of specific game titles and related elements

    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
    0:0.16
    1:0.19
    2:0.04
    3:0.04
    4:0.03
    5:0.03
    6:0.07
    7:0.09
    8:0.03
    9:0.04
    10:0.18
    11:0.05
    Negative Logits
     Tsu
    -3.28
     Pom
    -2.97
     nuns
    -2.76
     Hawkins
    -2.75
     Survivors
    -2.75
     Sawyer
    -2.74
     flush
    -2.70
     Watson
    -2.69
     nap
    -2.64
     Faw
    -2.63
    POSITIVE LOGITS
    EG
    6.18
    eg
    5.84
     EG
    5.18
     Eg
    4.71
     eg
    3.90
     Peg
    3.82
     Eag
    3.64
     Ples
    3.60
    eneg
    3.56
     Eth
    3.50
    Activations Density 0.001%

    No Known Activations