© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 3-ATT-KK
    11. 7188
    Prev
    Next
    INDEX
    Explanations

    references to explosives and explosive devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.05
    3:0.06
    4:0.04
    5:0.09
    6:0.10
    7:0.30
    8:0.05
    9:0.04
    10:0.09
    11:0.07
    Negative Logits
     Tribe
    -1.32
     Rae
    -1.27
     Dinosaur
    -1.20
    soType
    -1.14
    College
    -1.12
    Tre
    -1.09
    Madison
    -1.08
    SEA
    -1.07
    ゴン
    -1.07
     Username
    -1.06
    POSITIVE LOGITS
     deton
    1.71
     projectiles
    1.58
     inciner
    1.51
     combustion
    1.50
     Explos
    1.45
     explosives
    1.43
     explosion
    1.39
     projectile
    1.37
     grenade
    1.37
     ignition
    1.37
    Activations Density 0.143%

    No Known Activations