© 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. 27738
    Prev
    Next
    INDEX
    Explanations

    mentions of government or authority-related entities

    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
    2:0.09
    3:0.07
    4:0.05
    5:0.06
    6:0.11
    7:0.03
    8:0.09
    9:0.07
    10:0.14
    11:0.21
    Negative Logits
    capacity
    -1.48
    BuyableInstoreAndOnline
    -1.46
    arus
    -1.44
     sqor
    -1.44
    ivery
    -1.43
    responsible
    -1.38
    ika
    -1.35
     Centauri
    -1.32
    arding
    -1.31
    ��
    -1.29
    POSITIVE LOGITS
     passer
    1.55
    Twitter
    1.43
     Youtube
    1.42
     fastball
    1.36
     Sammy
    1.36
     itch
    1.34
     skate
    1.34
     UFC
    1.34
     youtube
    1.33
     audition
    1.32
    Activations Density 0.014%

    No Known Activations