© 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. 5-ATT-KK
    11. 43469
    Prev
    Next
    INDEX
    Explanations

    references to Kim Jong Un and his leadership role in North Korea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    1:0.00
    2:0.12
    3:0.06
    4:0.07
    5:0.03
    6:0.04
    7:0.06
    8:0.05
    9:0.03
    10:0.33
    11:0.13
    Negative Logits
     scrut
    -1.61
    arge
    -1.53
     abst
    -1.51
     gravel
    -1.45
    Recommend
    -1.35
    nil
    -1.32
    �
    -1.31
    cill
    -1.30
     fundament
    -1.27
     tow
    -1.27
    POSITIVE LOGITS
     Jinping
    1.58
    hya
    1.49
     reincarn
    1.39
    iphate
    1.39
    creator
    1.39
    renheit
    1.37
    itcher
    1.35
    senal
    1.30
    lov
    1.30
    ulhu
    1.25
    Activations Density 0.013%

    No Known Activations