© 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. 9-ATT-KK
    6. 19185
    Prev
    Next
    INDEX
    Explanations

    names and references to individuals related to financial and political contexts

    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
    0:0.16
    1:0.02
    2:0.11
    3:0.05
    4:0.02
    5:0.10
    6:0.04
    7:0.09
    8:0.27
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
    elaide
    -3.45
    ğ
    -3.36
     Alic
    -3.33
    stanbul
    -3.22
     Choi
    -3.22
     Istanbul
    -3.14
     PKK
    -3.13
     Ankara
    -3.10
    �
    -2.95
    Turkish
    -2.94
    POSITIVE LOGITS
    Romney
    6.92
     Romney
    6.65
     Bain
    5.45
     Mitt
    5.06
     Santorum
    4.65
     Massachusetts
    4.57
     Mormonism
    4.28
     Gingrich
    4.25
     Mormon
    4.11
    Utah
    4.02
    Activations Density 0.065%

    No Known Activations