© 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. 3-ATT-KK
    6. 11039
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to social and cultural issues, especially those involving political or economic implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.25
    3:0.07
    4:0.01
    5:0.03
    6:0.05
    7:0.13
    8:0.10
    9:0.13
    10:0.07
    11:0.06
    Negative Logits
     Saudi
    -0.99
     Proud
    -0.96
     Uzbek
    -0.95
     ranking
    -0.94
     Omaha
    -0.94
     blessed
    -0.94
     Onion
    -0.94
     Zap
    -0.93
     Tracker
    -0.91
     Riyadh
    -0.90
    POSITIVE LOGITS
    quit
    1.28
    edge
    1.18
    itely
    1.13
    igate
    1.12
    ensibly
    1.12
    MpServer
    1.11
     oneself
    1.10
    illy
    1.10
    Effects
    1.07
    hair
    1.06
    Activations Density 0.115%

    No Known Activations