© 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. 20458
    Prev
    Next
    INDEX
    Explanations

    references to geographical and political entities as well as disputes involving them

    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
    0:0.04
    1:0.08
    2:0.05
    3:0.06
    4:0.06
    5:0.02
    6:0.04
    7:0.10
    8:0.37
    9:0.03
    10:0.05
    11:0.04
    Negative Logits
     dexter
    -2.04
    near
    -2.02
    foundation
    -1.96
     utmost
    -1.96
     Reborn
    -1.94
    intendent
    -1.93
     Quan
    -1.92
    onen
    -1.88
     Canaver
    -1.85
     seeker
    -1.79
    POSITIVE LOGITS
     is
    4.32
     was
    3.57
    Is
    3.44
    is
    3.43
    was
    3.31
     Is
    3.02
     has
    2.87
     may
    2.80
     =
    2.72
     consists
    2.62
    Activations Density 0.060%

    No Known Activations