© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 19494
    Prev
    Next
    INDEX
    Explanations

    references to Poland and its relationships or status with other countries

    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
    0:0.06
    1:0.02
    2:0.02
    3:0.14
    4:0.09
    5:0.02
    6:0.02
    7:0.40
    8:0.02
    9:0.02
    10:0.03
    11:0.09
    Negative Logits
    Pol
    -3.15
    orks
    -3.08
     Pol
    -2.96
    ork
    -2.86
    ️
    -2.82
    pole
    -2.80
    brown
    -2.76
    pol
    -2.76
     Poc
    -2.74
     BCC
    -2.74
    POSITIVE LOGITS
     Hungary
    2.51
     Ars
    2.39
     Dag
    2.32
     Hess
    2.31
     Breaker
    2.29
     breaker
    2.28
     Dominic
    2.26
     Emirates
    2.25
     Arbit
    2.22
     Stevenson
    2.21
    Activations Density 0.009%

    No Known Activations