© 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. 10-ATT-KK
    11. 20895
    Prev
    Next
    INDEX
    Explanations

    references to political figures and events in Northern Ireland

    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
    0:0.43
    1:0.03
    2:0.03
    3:0.06
    4:0.06
    5:0.03
    6:0.05
    7:0.10
    8:0.02
    9:0.04
    10:0.05
    11:0.04
    Negative Logits
    Egypt
    -4.58
    Tesla
    -4.47
     Tesla
    -4.32
     Elon
    -4.17
     Egyptian
    -4.13
     Nile
    -4.11
     Mubarak
    -4.08
     Grizzlies
    -4.01
     Egyptians
    -3.97
     Panda
    -3.84
    POSITIVE LOGITS
    Ireland
    7.53
     Ireland
    7.14
     Ulster
    7.07
     Irish
    7.03
    Irish
    6.94
     Dublin
    6.76
     Cork
    6.47
     Belfast
    6.30
     Sinn
    5.90
     Gael
    5.76
    Activations Density 0.136%

    No Known Activations