© 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. 12576
    Prev
    Next
    INDEX
    Explanations

    references to age and location within a context, particularly related to individuals

    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
    0:0.18
    1:0.10
    2:0.05
    3:0.05
    4:0.04
    5:0.05
    6:0.06
    7:0.07
    8:0.05
    9:0.06
    10:0.20
    11:0.04
    Negative Logits
     BCC
    -3.86
     MC
    -3.63
     McAuliffe
    -3.46
     McDonnell
    -3.44
    Minecraft
    -3.26
     BAT
    -3.14
     Cerberus
    -3.08
     McGr
    -3.03
    Batman
    -3.03
     Ceres
    -3.00
    POSITIVE LOGITS
     Turk
    9.15
    Tur
    5.86
     Uzbek
    5.48
     Turks
    5.03
     Helsinki
    3.99
    zbek
    3.94
     tur
    3.80
     Taj
    3.75
     Hels
    3.74
     Finland
    3.71
    Activations Density 0.001%

    No Known Activations