© 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. 2083
    Prev
    Next
    INDEX
    Explanations

    references to political failures and criticisms of government actions

    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
    0:0.04
    1:0.02
    2:0.04
    3:0.05
    4:0.03
    5:0.04
    6:0.03
    7:0.04
    8:0.58
    9:0.03
    10:0.02
    11:0.02
    Negative Logits
     Cavs
    -3.71
     Toledo
    -3.70
     Cleveland
    -3.64
    Denver
    -3.54
    Spanish
    -3.49
     Baghd
    -3.37
     Cavaliers
    -3.31
     Catalan
    -3.25
    Colorado
    -3.24
     Iraqi
    -3.22
    POSITIVE LOGITS
     Auckland
    8.92
     Kiw
    8.51
     NZ
    8.34
    uckland
    8.21
    NZ
    7.98
     Wellington
    7.42
     Tasman
    6.26
    nz
    6.11
     Zealand
    5.71
     Fiji
    5.45
    Activations Density 0.172%

    No Known Activations