© 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. 10-ATT-KK
    11. 17322
    Prev
    Next
    INDEX
    Explanations

    topics related to international conflicts and humanitarian crises, particularly emphasizing the situation in Yemen

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.12
    1:0.02
    2:0.03
    3:0.08
    4:0.07
    5:0.03
    6:0.02
    7:0.39
    8:0.02
    9:0.05
    10:0.05
    11:0.09
    Negative Logits
     salmon
    -2.99
     Saturn
    -2.92
    Seattle
    -2.87
    】
    -2.71
     Tenn
    -2.70
     Newcastle
    -2.69
     Mariners
    -2.66
     Tsuk
    -2.63
    keley
    -2.62
     Adelaide
    -2.58
    POSITIVE LOGITS
     Pil
    2.85
     Pillar
    2.65
     arming
    2.60
     statically
    2.55
    pit
    2.44
    Filename
    2.37
     policing
    2.36
     pil
    2.35
     ISIL
    2.33
     ply
    2.32
    Activations Density 0.004%

    No Known Activations