© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 19239
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals involved in political or social controversies, particularly regarding extradition and allegations of terrorism

    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
    0:0.21
    1:0.00
    2:0.21
    3:0.08
    4:0.04
    5:0.10
    6:0.03
    7:0.04
    8:0.19
    9:0.02
    10:0.03
    11:0.01
    Negative Logits
    aux
    -2.96
    illac
    -2.89
     Explorer
    -2.84
    obyl
    -2.81
    ennes
    -2.80
     Corvette
    -2.78
     Coral
    -2.78
    byss
    -2.76
     coral
    -2.75
    abeth
    -2.74
    POSITIVE LOGITS
     Gul
    6.31
     Erdogan
    4.39
    Turkish
    3.71
    ullah
    3.65
     Turkish
    3.63
     Recep
    3.59
    Turkey
    3.56
     cleric
    3.53
     Uzbek
    3.47
     Turkey
    3.45
    Activations Density 0.004%

    No Known Activations