© 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. 12143
    Prev
    Next
    INDEX
    Explanations

    instances of violent actions and military terminology, especially related to firearms and projectiles

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.02
    2:0.04
    3:0.04
    4:0.05
    5:0.15
    6:0.02
    7:0.07
    8:0.01
    9:0.39
    10:0.02
    11:0.06
    Negative Logits
     consult
    -2.73
     rethink
    -2.56
     adop
    -2.56
     Improvement
    -2.54
     inquire
    -2.54
     reconsider
    -2.43
     realization
    -2.41
     rejoice
    -2.41
     consultation
    -2.39
     Unch
    -2.39
    POSITIVE LOGITS
     hurled
    3.02
     projectiles
    2.77
     lethal
    2.76
     detonated
    2.75
     warheads
    2.69
    pperc
    2.68
    lethal
    2.66
    bomb
    2.65
     grenades
    2.62
     volley
    2.61
    Activations Density 0.260%

    No Known Activations