© 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. 5074
    Prev
    Next
    INDEX
    Explanations

    mentions of proper nouns or specific entities, particularly personal names and locations

    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
    0:0.09
    1:0.04
    2:0.06
    3:0.07
    4:0.04
    5:0.06
    6:0.17
    7:0.05
    8:0.07
    9:0.22
    10:0.03
    11:0.04
    Negative Logits
    Rap
    -3.25
    rup
    -3.11
     FP
    -3.11
    FP
    -3.10
    op
    -3.04
     Pose
    -3.04
    roxy
    -3.01
     2019
    -2.94
     KP
    -2.94
     EP
    -2.91
    POSITIVE LOGITS
     Waterloo
    3.32
     Lann
    3.11
     Luthor
    3.01
     Yar
    2.96
    iard
    2.93
     Lauder
    2.91
     Aber
    2.90
    Taylor
    2.87
     Alz
    2.87
     Nanto
    2.83
    Activations Density 0.001%

    No Known Activations