© 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. 27950
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to military or law enforcement contexts

    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
    0:0.04
    1:0.04
    2:0.04
    3:0.03
    4:0.05
    5:0.04
    6:0.54
    7:0.04
    8:0.02
    9:0.03
    10:0.05
    11:0.02
    Negative Logits
    reviewed
    -1.43
    ruary
    -1.37
    awaited
    -1.26
    Kal
    -1.24
    alore
    -1.23
     shore
    -1.22
    atform
    -1.18
    levard
    -1.18
    ufact
    -1.18
    antz
    -1.17
    POSITIVE LOGITS
     constitu
    1.50
    ibles
    1.42
    llah
    1.39
    opic
    1.36
    rouse
    1.35
    overe
    1.33
     kindred
    1.29
    omal
    1.29
     signatures
    1.28
    aiman
    1.28
    Activations Density 0.020%

    No Known Activations