© 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. 12528
    Prev
    Next
    INDEX
    Explanations

    comments about political accountability and leadership decisions

    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
    0:0.17
    1:0.04
    2:0.07
    3:0.05
    4:0.04
    5:0.01
    6:0.19
    7:0.18
    8:0.01
    9:0.04
    10:0.11
    11:0.03
    Negative Logits
     Valiant
    -2.81
     rac
    -2.71
     Paraly
    -2.66
     chess
    -2.57
     Pikachu
    -2.56
     Chennai
    -2.54
     LTD
    -2.49
     Suk
    -2.45
     Lovecraft
    -2.45
     Stard
    -2.45
    POSITIVE LOGITS
     Boehner
    6.56
     Cantor
    3.22
     Speaker
    3.21
    グ
    2.97
    House
    2.96
     Limbaugh
    2.86
    Senate
    2.83
     speaker
    2.80
     Pelosi
    2.69
     House
    2.69
    Activations Density 0.022%

    No Known Activations