© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 14445
    Prev
    Next
    INDEX
    Explanations

    elements related to individuals' names and titles

    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
    1:0.02
    2:0.04
    3:0.07
    4:0.03
    5:0.04
    6:0.12
    7:0.02
    8:0.04
    9:0.50
    10:0.02
    11:0.02
    Negative Logits
     Kitt
    -3.54
    GMT
    -3.45
     Ich
    -3.35
    Haw
    -3.28
     Kent
    -3.04
     emb
    -3.04
     appendix
    -2.97
     whales
    -2.93
    emb
    -2.93
     Ghosts
    -2.92
    POSITIVE LOGITS
    R
    6.15
     Raz
    5.87
    Rs
    5.64
     RA
    5.38
     Ri
    5.32
     R
    5.30
    RA
    5.21
    r
    5.20
    RP
    5.12
     Rav
    5.09
    Activations Density 0.514%

    No Known Activations