© 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. 17043
    Prev
    Next
    INDEX
    Explanations

    phrases indicating political or relational dynamics between countries or entities

    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
    0:0.02
    1:0.02
    2:0.02
    3:0.03
    4:0.05
    5:0.09
    6:0.02
    7:0.05
    8:0.02
    9:0.56
    10:0.01
    11:0.05
    Negative Logits
     unemploy
    -2.44
    Its
    -2.03
    teness
    -1.91
    umper
    -1.86
     Its
    -1.75
    Demand
    -1.75
    Shock
    -1.75
    undown
    -1.73
    Downloadha
    -1.72
     offender
    -1.69
    POSITIVE LOGITS
     respectively
    5.92
     together
    5.29
    together
    5.19
     mutually
    4.69
     Together
    4.52
     jointly
    4.51
     apiece
    4.44
     unison
    4.44
     mutual
    4.42
    Together
    4.32
    Activations Density 1.713%

    No Known Activations