© 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. 8461
    Prev
    Next
    INDEX
    Explanations

    discussions around international relations and diplomatic negotiations

    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
    0:0.07
    1:0.03
    2:0.04
    3:0.13
    4:0.19
    5:0.06
    6:0.08
    7:0.12
    8:0.02
    9:0.13
    10:0.03
    11:0.05
    Negative Logits
     Weird
    -3.02
     haun
    -2.66
    Favorite
    -2.63
     Mystery
    -2.60
     trivia
    -2.47
     Died
    -2.42
    osaurus
    -2.42
    maxwell
    -2.40
     ain
    -2.31
     Famous
    -2.29
    POSITIVE LOGITS
     ceasefire
    4.05
     Nato
    3.77
     urgently
    3.77
     diplomatic
    3.63
     recognise
    3.56
     Syrians
    3.49
     UNCLASSIFIED
    3.38
     cease
    3.38
     condemn
    3.38
     Palestinians
    3.32
    Activations Density 0.603%

    No Known Activations