© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 10872
    Prev
    Next
    INDEX
    Explanations

    the presence of notable events or gatherings related to Chicago

    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
    1:0.01
    2:0.04
    3:0.30
    4:0.02
    5:0.08
    6:0.02
    7:0.09
    8:0.26
    9:0.01
    10:0.03
    11:0.04
    Negative Logits
     Asgard
    -2.76
     Caucasus
    -2.56
     Titan
    -2.39
    ptoms
    -2.33
     Predators
    -2.30
     instruments
    -2.27
    ussian
    -2.22
     Bolshe
    -2.19
    ック
    -2.19
     technological
    -2.17
    POSITIVE LOGITS
     Mex
    2.94
    Mex
    2.77
     Luna
    2.75
     Fiesta
    2.73
    Catholic
    2.64
     Coy
    2.59
     Cardinal
    2.56
     Stanton
    2.56
     Mexican
    2.52
    FML
    2.50
    Activations Density 0.001%

    No Known Activations