© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 7850
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations and the framing of narratives related to those places

    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
    0:0.12
    1:0.08
    2:0.06
    3:0.06
    4:0.05
    5:0.02
    6:0.11
    7:0.13
    8:0.03
    9:0.04
    10:0.15
    11:0.08
    Negative Logits
    aga
    -2.84
    gra
    -2.56
     referen
    -2.54
     Fairy
    -2.52
    tun
    -2.44
     Gö
    -2.43
     Sou
    -2.40
     por
    -2.37
    worms
    -2.35
     Quadro
    -2.32
    POSITIVE LOGITS
     Jude
    5.92
     Galile
    3.56
     Jud
    3.31
    Jer
    3.27
     Jericho
    3.13
     Samson
    3.07
     evangel
    3.06
     Kash
    2.97
     Samar
    2.94
     Jessie
    2.72
    Activations Density 0.002%

    No Known Activations