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. 7-ATT-KK
    6. 18805
    Prev
    Next
    INDEX
    Explanations

    names of geographic locations and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.7.attn.hook_z
    Hook Layer
    7
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.05
    2:0.11
    3:0.04
    4:0.04
    5:0.05
    6:0.05
    7:0.06
    8:0.03
    9:0.03
    10:0.37
    11:0.06
    Negative Logits
    iage
    -2.29
    ifix
    -2.23
    ido
    -2.15
    upp
    -2.13
    ider
    -2.11
    ificial
    -2.10
     Mustang
    -2.08
    381
    -2.06
    tumblr
    -2.02
    emy
    -2.01
    POSITIVE LOGITS
    Region
    4.29
     regions
    3.73
    region
    3.73
     Regions
    3.68
     Region
    3.55
     region
    3.46
     Regional
    2.78
    RW
    2.61
     Areas
    2.32
     RW
    2.30
    Activations Density 0.001%

    No Known Activations