© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 6522
    Prev
    Next
    INDEX
    Explanations

    discussions about video games, particularly focusing on their development, release details, and player feedback

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.11
    1:0.03
    2:0.12
    3:0.06
    4:0.05
    5:0.08
    6:0.11
    7:0.06
    8:0.17
    9:0.08
    10:0.03
    11:0.05
    Negative Logits
     mathemat
    -3.75
    Bron
    -3.53
    olkien
    -3.49
     Lann
    -3.47
    Balt
    -3.44
    BOOK
    -3.44
    Tal
    -3.15
     Pars
    -3.13
    ython
    -3.11
    ################
    -3.08
    POSITIVE LOGITS
     Resident
    8.29
     Capcom
    6.56
     Romero
    4.34
     Ryu
    4.22
     EV
    4.02
     Metroid
    3.83
     Eva
    3.82
     Psycho
    3.81
     resident
    3.79
     Canaver
    3.77
    Activations Density 0.004%

    No Known Activations