© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 14596
    Prev
    Next
    INDEX
    Explanations

    terms related to international trade agreements and economic relationships

    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
    0:0.06
    1:0.01
    2:0.08
    3:0.41
    4:0.02
    5:0.10
    6:0.02
    7:0.04
    8:0.07
    9:0.01
    10:0.11
    11:0.02
    Negative Logits
     staffers
    -2.78
     interns
    -2.57
     employees
    -2.37
     nerds
    -2.34
    aughs
    -2.31
     actresses
    -2.31
     DJs
    -2.31
     reviewers
    -2.29
     professionals
    -2.24
     comedians
    -2.22
    POSITIVE LOGITS
     ceasefire
    2.84
     treaty
    2.77
     bilateral
    2.72
     truce
    2.68
     Nato
    2.64
     Strait
    2.63
     treaties
    2.61
     NATO
    2.55
     Agreement
    2.51
     Syria
    2.49
    Activations Density 0.738%

    No Known Activations