Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14558
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and statistics related to immigration issues

    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
    0:0.22
    1:0.03
    2:0.04
    3:0.10
    4:0.05
    5:0.02
    6:0.07
    7:0.10
    8:0.01
    9:0.04
    10:0.22
    11:0.04
    Negative Logits
     Indy
    -3.76
     Iro
    -3.74
     Barrett
    -3.67
    Mex
    -3.58
    iOS
    -3.50
     Mayweather
    -3.37
     Indianapolis
    -3.33
     Guerrero
    -3.23
     Pryor
    -3.21
     Colts
    -3.17
    POSITIVE LOGITS
     Copenhagen
    8.60
     Denmark
    8.59
     Danish
    8.32
     Scandinavian
    5.48
     Scandinav
    5.38
    gaard
    5.36
    ø
    5.23
     Lars
    4.92
    Den
    4.74
     Greenland
    4.73
    Activations Density 0.041%

    No Known Activations