© 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. 2-ATT-KK
    11. 16156
    Prev
    Next
    INDEX
    Explanations

    information about military operations and territories

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.06
    1:0.08
    2:0.04
    3:0.06
    4:0.03
    5:0.05
    6:0.09
    7:0.12
    8:0.08
    9:0.08
    10:0.16
    11:0.08
    Negative Logits
     Nerd
    -1.08
     commenters
    -1.06
     skept
    -1.04
     Doodle
    -1.00
     nerds
    -1.00
     thinker
    -0.97
     skepticism
    -0.96
     blogging
    -0.96
     philosopher
    -0.95
     bloggers
    -0.95
    POSITIVE LOGITS
    east
    1.33
    swick
    1.30
    ascus
    1.27
    addons
    1.18
    anwhile
    1.16
    abus
    1.16
    Syrian
    1.14
    veh
    1.13
    munition
    1.11
    AAF
    1.10
    Activations Density 0.441%

    No Known Activations