© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 20509
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and their actions in contexts related to news or events

    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
    0:0.07
    1:0.01
    2:0.06
    3:0.03
    4:0.05
    5:0.03
    6:0.25
    7:0.05
    8:0.07
    9:0.26
    10:0.03
    11:0.03
    Negative Logits
    ordan
    -3.89
    Egypt
    -3.88
     Jordanian
    -3.85
     crop
    -3.69
     Tiff
    -3.54
     Soy
    -3.44
     Rost
    -3.36
     seeded
    -3.34
    �
    -3.33
     Za
    -3.28
    POSITIVE LOGITS
     Murphy
    11.71
    Mur
    9.24
     Mur
    6.31
    mur
    6.04
     McCabe
    4.37
     Reilly
    4.29
     Myers
    4.21
     Sturgeon
    4.19
     Mercury
    4.18
     Sweeney
    4.08
    Activations Density 0.008%

    No Known Activations