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. 1-ATT-KK
    6. 6343
    Prev
    Next
    INDEX
    Explanations

    countries or geopolitical terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L1_Hcat_z_lr1.20e-03_l18.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v5.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.1.attn.hook_z
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.11
    2:0.15
    3:0.04
    4:0.11
    5:0.13
    6:0.03
    7:0.05
    8:0.04
    9:0.03
    10:0.11
    11:0.12
    Negative Logits
    iev
    -0.98
    ESE
    -0.89
    enger
    -0.86
    iesel
    -0.83
    fs
    -0.83
    illion
    -0.82
    ulla
    -0.81
    amazon
    -0.80
    :(
    -0.80
    gged
    -0.79
    POSITIVE LOGITS
     culminating
    1.07
     etc
    1.05
     albeit
    0.97
    conservancy
    0.96
     namely
    0.94
     presumably
    0.94
     disapp
    0.90
     agre
    0.89
     LLP
    0.85
     toile
    0.85
    Activations Density 0.755%

    No Known Activations