© 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. 10-ATT-KK
    11. 14774
    Prev
    Next
    INDEX
    Explanations

    references to locations and events involving people or groups in conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.27
    1:0.04
    2:0.04
    3:0.06
    4:0.05
    5:0.02
    6:0.06
    7:0.13
    8:0.02
    9:0.04
    10:0.19
    11:0.04
    Negative Logits
     Tanner
    -3.68
     Weber
    -3.67
     Lois
    -3.32
     Ames
    -3.29
     Scion
    -3.09
     McKenna
    -3.08
     Highlander
    -3.05
     Perry
    -3.02
    Seattle
    -3.01
     Stout
    -3.00
    POSITIVE LOGITS
     Gamb
    9.49
     Senegal
    4.84
     Gam
    3.92
     gamb
    3.91
     GAM
    3.79
     Maurit
    3.77
     Hispan
    3.68
     Jam
    3.68
     Augusta
    3.60
     Ghana
    3.47
    Activations Density 0.001%

    No Known Activations