© 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. 2198
    Prev
    Next
    INDEX
    Explanations

    references to individuals or entities in statements

    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
    3:0.05
    4:0.05
    5:0.03
    6:0.15
    7:0.02
    8:0.06
    9:0.45
    10:0.01
    11:0.02
    Negative Logits
     suppress
    -3.32
    309
    -3.26
    ANCE
    -3.22
     309
    -3.19
     Contra
    -3.17
     Fairfax
    -3.17
    Egypt
    -3.15
     Niger
    -3.09
     Alger
    -3.06
     Roger
    -3.03
    POSITIVE LOGITS
    K
    5.98
    k
    5.85
     Kad
    5.71
    kos
    5.55
     k
    5.49
     KP
    5.46
     Kir
    5.45
     Ki
    5.41
     Ker
    5.29
    ka
    5.27
    Activations Density 0.310%

    No Known Activations