© 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. 10-ATT-KK
    11. 12158
    Prev
    Next
    INDEX
    Explanations

    keywords related to visual quality and effects in video games

    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
    0:0.08
    1:0.03
    2:0.04
    3:0.04
    4:0.18
    5:0.04
    6:0.03
    7:0.29
    8:0.02
    9:0.06
    10:0.03
    11:0.11
    Negative Logits
    ratulations
    -2.38
    OGR
    -2.33
    ":[{"
    -2.27
    igraph
    -2.21
    ItemImage
    -2.21
     GF
    -2.18
    photo
    -2.13
    ":"","
    -2.13
     vanity
    -2.12
    idas
    -2.11
    POSITIVE LOGITS
     Capcom
    2.48
    hesda
    2.40
    atson
    2.25
     atmospheric
    2.21
    boss
    2.21
     condensed
    2.16
    coon
    2.13
     Bon
    2.13
     Chambers
    2.12
     Boss
    2.11
    Activations Density 0.058%

    No Known Activations