© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 3509
    Prev
    Next
    INDEX
    Explanations

    references to government departments and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.15
    1:0.01
    2:0.20
    3:0.05
    4:0.02
    5:0.09
    6:0.08
    7:0.03
    8:0.19
    9:0.07
    10:0.03
    11:0.02
    Negative Logits
     Ukip
    -3.32
     Bok
    -3.26
     SY
    -3.17
     Leafs
    -3.17
     Fighters
    -3.17
     Sai
    -3.16
     VS
    -3.14
     Synd
    -3.14
     NHS
    -3.09
     NXT
    -3.09
    POSITIVE LOGITS
     Interior
    5.54
     Zin
    5.54
     BLM
    4.13
     Yellowstone
    3.92
     canyon
    3.81
     desert
    3.80
     Navajo
    3.69
     ranch
    3.62
     ranc
    3.60
     grazing
    3.55
    Activations Density 0.003%

    No Known Activations