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

    Neuronpedia

    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. 11020
    Prev
    Next
    INDEX
    Explanations

    references to military actions and territorial changes in conflict zones

    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
    0:0.10
    1:0.02
    2:0.29
    3:0.10
    4:0.04
    5:0.09
    6:0.02
    7:0.07
    8:0.13
    9:0.02
    10:0.03
    11:0.02
    Negative Logits
     chirop
    -2.79
    Consumer
    -2.75
    ¢
    -2.75
     Oprah
    -2.65
     Epstein
    -2.56
     plagiar
    -2.52
    infeld
    -2.49
     Edison
    -2.47
     Gins
    -2.45
    ructose
    -2.42
    POSITIVE LOGITS
     siege
    4.54
     ceasefire
    4.53
     militants
    4.36
     Daesh
    4.35
     airstrikes
    4.32
     insurgents
    4.31
     ISIL
    4.31
     YPG
    4.24
     militia
    4.17
     fighters
    4.16
    Activations Density 0.719%

    No Known Activations