© 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. 39481
    Prev
    Next
    INDEX
    Explanations

    phrases that refer to political or military actions involving specific locations or entities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.01
    1:0.01
    2:0.18
    3:0.08
    4:0.13
    5:0.02
    6:0.03
    7:0.25
    8:0.04
    9:0.03
    10:0.10
    11:0.08
    Negative Logits
     faint
    -1.40
    aleigh
    -1.31
    okingly
    -1.31
     develops
    -1.28
    ients
    -1.27
     increments
    -1.26
    cellaneous
    -1.22
     pauses
    -1.21
    oqu
    -1.20
    abytes
    -1.20
    POSITIVE LOGITS
    INO
    1.32
     takeover
    1.25
     cannibal
    1.24
     dominance
    1.21
    prime
    1.21
     Crimean
    1.21
    venge
    1.20
     scapego
    1.19
    OTUS
    1.19
     Crimea
    1.18
    Activations Density 0.128%

    No Known Activations