© 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. 9-ATT-KK
    11. 18029
    Prev
    Next
    INDEX
    Explanations

    references to government officials and their titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.03
    2:0.06
    3:0.07
    4:0.06
    5:0.06
    6:0.18
    7:0.03
    8:0.05
    9:0.27
    10:0.02
    11:0.05
    Negative Logits
     Crow
    -4.17
     Tig
    -3.83
    uart
    -3.75
     Cic
    -3.67
     Rockies
    -3.64
     Valentine
    -3.63
     Cherokee
    -3.47
     Wolfe
    -3.44
     Louie
    -3.36
     Archie
    -3.33
    POSITIVE LOGITS
     minister
    6.80
     ministerial
    5.96
     ministers
    5.94
     ministry
    5.56
     Minister
    5.52
    minist
    5.29
     Ministers
    5.09
     ministries
    4.86
     Ministry
    4.53
    Min
    4.49
    Activations Density 0.005%

    No Known Activations