© 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. 14868
    Prev
    Next
    INDEX
    Explanations

    references to executive orders and related political actions

    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
    0:0.08
    1:0.04
    2:0.04
    3:0.07
    4:0.06
    5:0.02
    6:0.23
    7:0.14
    8:0.02
    9:0.07
    10:0.04
    11:0.12
    Negative Logits
    coni
    -2.96
    party
    -2.88
     Miliband
    -2.79
     councillor
    -2.57
     Lib
    -2.57
     ITV
    -2.53
     murd
    -2.46
    Lib
    -2.45
     Classical
    -2.44
    oola
    -2.41
    POSITIVE LOGITS
     Executive
    3.48
     HHS
    3.48
     DACA
    3.47
     orders
    3.39
     Orders
    3.33
     Pruitt
    3.30
     order
    3.28
     Mattis
    3.16
     executive
    3.16
     DOJ
    3.15
    Activations Density 0.070%

    No Known Activations