© 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. 5-ATT-KK
    11. 5224
    Prev
    Next
    INDEX
    Explanations

    phrases related to political tensions and conflicts between countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.07
    3:0.20
    4:0.05
    5:0.05
    6:0.01
    7:0.03
    8:0.07
    9:0.11
    10:0.18
    11:0.12
    Negative Logits
     goddamn
    -1.56
    hetic
    -1.55
     damn
    -1.43
     dude
    -1.42
     dudes
    -1.40
    acus
    -1.33
    osite
    -1.32
     fuckin
    -1.32
    .......
    -1.31
    brainer
    -1.31
    POSITIVE LOGITS
     toppled
    1.40
     blamed
    1.40
     raids
    1.32
     angered
    1.29
     fuelled
    1.29
     successive
    1.28
     reportedly
    1.28
     reliance
    1.27
     ousted
    1.26
     programmes
    1.25
    Activations Density 0.588%

    No Known Activations