© 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. 8932
    Prev
    Next
    INDEX
    Explanations

    references to geographical features and climatic conditions

    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
    0:0.12
    1:0.03
    2:0.04
    3:0.13
    4:0.15
    5:0.03
    6:0.04
    7:0.17
    8:0.02
    9:0.07
    10:0.04
    11:0.10
    Negative Logits
    UFC
    -2.26
     vetting
    -2.20
    fts
    -2.17
     boun
    -2.07
    ariat
    -2.06
    Street
    -2.06
     boycott
    -2.03
    URI
    -1.99
    Sports
    -1.99
    selling
    -1.98
    POSITIVE LOGITS
     northwestern
    2.73
     Alaska
    2.61
     Yellowstone
    2.60
     southeastern
    2.57
     Siberia
    2.52
     northeastern
    2.49
     pra
    2.46
     northern
    2.41
     bore
    2.36
     southwestern
    2.35
    Activations Density 0.128%

    No Known Activations