© 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. 19093
    Prev
    Next
    INDEX
    Explanations

    possessive forms indicating ownership or relationships

    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
    0:0.13
    1:0.02
    2:0.10
    3:0.06
    4:0.04
    5:0.06
    6:0.12
    7:0.07
    8:0.18
    9:0.10
    10:0.03
    11:0.04
    Negative Logits
    yk
    -3.65
    jen
    -3.65
    SK
    -3.58
     teasp
    -3.54
    ipeg
    -3.47
     KT
    -3.42
    OTS
    -3.41
    astern
    -3.35
    cki
    -3.28
     Kul
    -3.26
    POSITIVE LOGITS
     Dante
    9.85
     Purg
    5.96
     Inferno
    5.20
     Divine
    4.40
     Satan
    4.40
     Hades
    4.32
     Quentin
    4.20
     Lucifer
    4.12
     Inquisition
    4.11
     Augustine
    4.09
    Activations Density 0.000%

    No Known Activations