© 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. 9-ATT-KK
    11. 13458
    Prev
    Next
    INDEX
    Explanations

    references to the Syrian regime and its use of chemical weapons

    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
    0:0.31
    1:0.01
    2:0.09
    3:0.12
    4:0.02
    5:0.15
    6:0.02
    7:0.04
    8:0.12
    9:0.01
    10:0.04
    11:0.02
    Negative Logits
    wana
    -2.29
    alore
    -2.27
    Scotland
    -2.23
     Gibraltar
    -2.22
     Lak
    -2.22
    izons
    -2.18
     Bangalore
    -2.15
     Mahar
    -2.14
     Aberdeen
    -2.09
     Augusta
    -2.08
    POSITIVE LOGITS
     chemical
    2.56
    weet
    2.39
    icol
    2.12
     Syndrome
    2.07
    Sche
    2.06
     blender
    2.06
    Plex
    2.02
    ウス
    1.98
     syrup
    1.97
     Chemical
    1.95
    Activations Density 0.070%

    No Known Activations