© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11809
    Prev
    Next
    INDEX
    Explanations

    references to sporting statistics and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.04
    1:0.18
    2:0.03
    3:0.17
    4:0.03
    5:0.05
    6:0.03
    7:0.06
    8:0.08
    9:0.01
    10:0.05
    11:0.20
    Negative Logits
     Caucasus
    -2.36
     Yong
    -2.32
     ABE
    -2.30
     Silk
    -2.27
     yes
    -2.27
     thousands
    -2.21
     ----
    -2.18
     Alph
    -2.16
     Sina
    -2.16
     Bron
    -2.14
    POSITIVE LOGITS
    MpServer
    3.05
    ascript
    2.66
    onto
    2.62
    notation
    2.52
    thumbnails
    2.52
    Interstitial
    2.51
    Article
    2.46
    ItemThumbnailImage
    2.41
    20439
    2.39
    ­
    2.38
    Activations Density 0.002%

    No Known Activations