© 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. 5-ATT-KK
    11. 35343
    Prev
    Next
    INDEX
    Explanations

    key events and entities related to conflicts and humanitarian issues

    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
    0:0.01
    1:0.01
    2:0.45
    3:0.05
    4:0.07
    5:0.02
    6:0.02
    7:0.05
    8:0.04
    9:0.04
    10:0.11
    11:0.08
    Negative Logits
    ht
    -1.57
    ertodd
    -1.56
    Introduced
    -1.51
     dyed
    -1.45
    icient
    -1.43
     marg
    -1.43
    poon
    -1.42
     chopped
    -1.41
    cious
    -1.39
     exempted
    -1.39
    POSITIVE LOGITS
    Operation
    1.77
    Wars
    1.73
     underway
    1.58
    yrinth
    1.58
    ageddon
    1.56
    FML
    1.54
    uden
    1.54
     culminating
    1.52
    ursday
    1.50
     Kov
    1.46
    Activations Density 0.692%

    No Known Activations