© 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 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. 15013
    Prev
    Next
    INDEX
    Explanations

    references to military leadership and ranks within organizations

    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
    0:0.15
    1:0.02
    2:0.21
    3:0.14
    4:0.04
    5:0.09
    6:0.03
    7:0.05
    8:0.11
    9:0.03
    10:0.04
    11:0.03
    Negative Logits
    Tickets
    -2.73
     Fey
    -2.72
     Airbnb
    -2.65
     renters
    -2.62
     pedestrian
    -2.60
     pedestrians
    -2.55
    å
    -2.52
    estival
    -2.49
     Amsterdam
    -2.48
     bicycl
    -2.43
    POSITIVE LOGITS
     Petraeus
    4.44
     Mattis
    4.36
     commander
    4.34
     generals
    4.19
     Command
    4.18
     commanders
    4.12
     Commander
    3.90
     troop
    3.89
     Pentagon
    3.84
    Army
    3.83
    Activations Density 0.030%

    No Known Activations