© 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. 9-ATT-KK
    11. 10580
    Prev
    Next
    INDEX
    Explanations

    indicators of confusion or contradiction in statements

    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
    2:0.06
    3:0.03
    4:0.06
    5:0.04
    6:0.31
    7:0.04
    8:0.07
    9:0.20
    10:0.02
    11:0.03
    Negative Logits
    EVA
    -4.05
     Damon
    -3.81
     Spielberg
    -3.60
     Hyundai
    -3.59
     dam
    -3.38
     RTX
    -3.33
     Winston
    -3.30
     Mandela
    -3.29
    zee
    -3.28
     Truman
    -3.26
    POSITIVE LOGITS
     Mag
    10.60
    Mag
    10.07
     mag
    9.72
    mag
    8.65
     MAG
    7.31
    MAG
    6.87
    Magikarp
    6.02
     Magnet
    5.91
     Mage
    5.78
     Magical
    5.61
    Activations Density 0.017%

    No Known Activations