© 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. 3-ATT-KK
    11. 8736
    Prev
    Next
    INDEX
    Explanations

    names of cities and their surrounding areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.11
    1:0.04
    2:0.11
    3:0.03
    4:0.04
    5:0.03
    6:0.22
    7:0.05
    8:0.04
    9:0.05
    10:0.17
    11:0.05
    Negative Logits
     perpet
    -1.04
     truce
    -1.03
     incent
    -1.00
     territ
    -0.98
     convol
    -0.96
     mathemat
    -0.95
    ariat
    -0.94
     rall
    -0.93
     reconc
    -0.92
     bullish
    -0.89
    POSITIVE LOGITS
    ewater
    1.25
    apolis
    1.16
     Municipal
    0.98
     summers
    0.98
     winters
    0.96
    unia
    0.95
    iak
    0.95
     sew
    0.94
    ozo
    0.92
    wick
    0.92
    Activations Density 0.248%

    No Known Activations