© 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. 9-ATT-KK
    11. 13073
    Prev
    Next
    INDEX
    Explanations

    phrases related to happiness and well-being rankings of countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.04
    3:0.38
    4:0.03
    5:0.09
    6:0.02
    7:0.04
    8:0.07
    9:0.01
    10:0.18
    11:0.03
    Negative Logits
    rang
    -2.32
    autions
    -2.18
    Ts
    -2.06
    Repe
    -1.96
    NetMessage
    -1.95
    kas
    -1.92
    ittees
    -1.90
    erred
    -1.84
    >[
    -1.83
    lav
    -1.83
    POSITIVE LOGITS
     world
    2.50
     universe
    2.39
     humankind
    2.38
     worldwide
    2.34
     anywhere
    2.32
     America
    2.29
     neuroscience
    2.29
     globally
    2.21
     planet
    2.20
     Americas
    2.17
    Activations Density 0.178%

    No Known Activations