© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 24102
    Prev
    Next
    INDEX
    Explanations

    references to chemical weapons and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.14
    1:0.01
    2:0.28
    3:0.09
    4:0.01
    5:0.14
    6:0.03
    7:0.04
    8:0.14
    9:0.02
    10:0.03
    11:0.02
    Negative Logits
     Mormonism
    -2.62
     incumb
    -2.59
     Bonds
    -2.56
     retire
    -2.51
     Debt
    -2.47
     Taxes
    -2.41
     Marriage
    -2.39
     millionaires
    -2.38
     Wallet
    -2.38
     mortg
    -2.36
    POSITIVE LOGITS
     chemical
    4.55
     Chemical
    4.30
     chlorine
    4.29
    Chem
    3.86
     Assad
    3.72
    Assad
    3.64
     Damascus
    3.64
    Syrian
    3.63
    Syria
    3.54
     Idlib
    3.49
    Activations Density 0.074%

    No Known Activations