© 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. 19981
    Prev
    Next
    INDEX
    Explanations

    references to government departments and their activities related to economic and public safety issues

    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
    0:0.08
    1:0.02
    2:0.08
    3:0.05
    4:0.04
    5:0.06
    6:0.09
    7:0.05
    8:0.34
    9:0.09
    10:0.03
    11:0.03
    Negative Logits
     Ecuador
    -4.08
     Venezuelan
    -4.07
     Venezuela
    -3.78
     Venezuel
    -3.58
     Urug
    -3.56
     Panama
    -3.42
     Chavez
    -3.42
     Colombia
    -3.40
     Britann
    -3.38
     Krypt
    -3.35
    POSITIVE LOGITS
     Illinois
    6.47
    inois
    5.09
    Ill
    4.43
     IL
    4.38
    Iowa
    4.33
    Michigan
    4.25
    Indiana
    4.20
     ILCS
    4.16
     Iowa
    3.86
     Purdue
    3.81
    Activations Density 0.011%

    No Known Activations