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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 10573
    Prev
    Next
    INDEX
    Explanations

    references to the Girl Scouts organization and its programs

    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
    0:0.20
    1:0.01
    2:0.21
    3:0.06
    4:0.03
    5:0.07
    6:0.11
    7:0.04
    8:0.11
    9:0.05
    10:0.02
    11:0.02
    Negative Logits
     reper
    -3.95
    pour
    -3.59
     arter
    -3.43
    Nit
    -3.33
     membranes
    -3.28
    osph
    -3.26
     oxidative
    -3.24
     compr
    -3.24
     congest
    -3.17
     congestion
    -3.15
    POSITIVE LOGITS
     Scout
    6.40
     Scouts
    6.38
     Scouting
    6.35
     scout
    4.99
     troop
    4.99
     Girl
    4.95
     scouts
    4.87
     scouting
    4.50
     Boy
    4.24
     Girls
    3.88
    Activations Density 0.014%

    No Known Activations