© 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. 12405
    Prev
    Next
    INDEX
    Explanations

    instances of names and titles, particularly in a political context

    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
    0:0.16
    1:0.14
    2:0.08
    3:0.07
    4:0.05
    5:0.03
    6:0.09
    7:0.06
    8:0.03
    9:0.05
    10:0.14
    11:0.05
    Negative Logits
     Dinosaur
    -3.71
     QR
    -3.39
     Magnetic
    -3.25
     MAG
    -3.13
     pol
    -3.09
     PJ
    -3.03
     Duel
    -3.00
     FN
    -2.98
    paio
    -2.97
     Navajo
    -2.92
    POSITIVE LOGITS
     Hastings
    8.35
     Ashton
    7.30
     Lans
    4.03
     Kut
    3.82
    Ash
    3.68
     Hamb
    3.66
     Hoffman
    3.60
     Hansen
    3.56
    fleet
    3.55
     Ezek
    3.53
    Activations Density 0.002%

    No Known Activations