© 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. 11810
    Prev
    Next
    INDEX
    Explanations

    mentions of military personnel and related incidents

    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
    1:0.03
    2:0.06
    3:0.03
    4:0.06
    5:0.03
    6:0.23
    7:0.04
    8:0.07
    9:0.26
    10:0.02
    11:0.03
    Negative Logits
     Chocobo
    -4.18
     Clarkson
    -3.72
    leigh
    -3.64
     whip
    -3.59
     swaps
    -3.57
     Cobb
    -3.48
     Matthews
    -3.44
     shrimp
    -3.43
     MacDonald
    -3.41
    idia
    -3.39
    POSITIVE LOGITS
     Ur
    10.28
    Ur
    9.22
     UR
    7.58
     ur
    6.97
     Uri
    5.58
     URI
    5.35
     pee
    4.74
    URI
    4.57
    UR
    4.41
     Hur
    4.38
    Activations Density 0.002%

    No Known Activations