© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 21898
    Prev
    Next
    INDEX
    Explanations

    mentions of coalition and related political or military group dynamics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.06
    3:0.03
    4:0.05
    5:0.04
    6:0.03
    7:0.07
    8:0.05
    9:0.04
    10:0.39
    11:0.15
    Negative Logits
    Fax
    -1.66
    opathy
    -1.41
     sermon
    -1.36
     virginity
    -1.34
    abilia
    -1.32
     motivational
    -1.31
    VERTISEMENT
    -1.30
     Oprah
    -1.29
    ��
    -1.28
     Fres
    -1.27
    POSITIVE LOGITS
    ittee
    1.51
     controls
    1.46
    ledged
    1.44
    coal
    1.42
     negotiators
    1.40
    aughtered
    1.38
     coalition
    1.38
    BAT
    1.38
    unity
    1.36
     assembled
    1.36
    Activations Density 0.019%

    No Known Activations