© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14140
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue and quotes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.20
    1:0.07
    2:0.07
    3:0.08
    4:0.06
    5:0.03
    6:0.12
    7:0.10
    8:0.02
    9:0.06
    10:0.08
    11:0.06
    Negative Logits
     Higgins
    -3.52
     Leica
    -3.45
     Duff
    -3.41
    Spider
    -3.33
    cig
    -3.24
     Dudley
    -3.22
     bunny
    -3.21
     Reilly
    -3.20
     Newtown
    -3.19
     McGu
    -3.12
    POSITIVE LOGITS
     Civilization
    6.62
     Civ
    6.39
     civ
    4.63
     civilizations
    4.63
     civilization
    4.13
     Sett
    3.81
     Empires
    3.63
     diplomacy
    3.58
     sett
    3.57
     Diplom
    3.57
    Activations Density 0.002%

    No Known Activations