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

    Neuronpedia

    Jacobian LensNEW
    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. 9394
    Prev
    Next
    INDEX
    Explanations

    names of organizations and entities involved in legal and ethical discussions or controversies

    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
    0:0.06
    1:0.02
    2:0.05
    3:0.13
    4:0.03
    5:0.06
    6:0.03
    7:0.05
    8:0.42
    9:0.02
    10:0.04
    11:0.03
    Negative Logits
     Tao
    -3.72
     India
    -3.53
     Singh
    -3.38
     CBI
    -3.25
     Slovakia
    -3.21
     Xander
    -3.18
    India
    -3.17
     Hung
    -3.15
     Narendra
    -3.12
     Sanskrit
    -3.09
    POSITIVE LOGITS
     Cairo
    4.94
     Beirut
    4.89
     Ibn
    4.88
    Arab
    4.78
    Egypt
    4.72
     ibn
    4.68
     Hezbollah
    4.42
    zbollah
    4.41
     Arab
    4.39
     Tunis
    4.28
    Activations Density 0.045%

    No Known Activations