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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14845
    Prev
    Next
    INDEX
    Explanations

    concepts related to geographic and political references involving regions and settlements

    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
    0:0.28
    1:0.03
    2:0.03
    3:0.09
    4:0.06
    5:0.03
    6:0.07
    7:0.17
    8:0.02
    9:0.06
    10:0.08
    11:0.03
    Negative Logits
     Poe
    -3.75
     Valkyrie
    -3.74
     UFO
    -3.62
     Starship
    -3.37
     Oswald
    -3.35
     aircraft
    -3.16
     UFOs
    -3.13
     Cruise
    -3.11
     planes
    -3.10
     Varg
    -3.07
    POSITIVE LOGITS
     Eli
    3.35
     Bethlehem
    3.35
     Heb
    3.32
     almond
    3.25
     almonds
    3.25
     Milk
    3.19
    maxwell
    3.06
     Barclays
    3.04
     Canterbury
    2.96
     dairy
    2.94
    Activations Density 0.001%

    No Known Activations