© 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. 3415
    Prev
    Next
    INDEX
    Explanations

    specific entities and their relationships within written content, particularly focusing on individuals' names and phrases referring to political contexts or 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
    0:0.07
    1:0.03
    2:0.11
    3:0.06
    4:0.04
    5:0.09
    6:0.07
    7:0.12
    8:0.26
    9:0.03
    10:0.04
    11:0.04
    Negative Logits
     Allaah
    -3.75
     Zion
    -3.68
     Sabbath
    -3.50
     borough
    -3.35
     Yorkshire
    -3.28
     Jericho
    -3.22
     Warwick
    -3.18
     Palestine
    -3.17
     Kidd
    -3.15
     Canaan
    -3.13
    POSITIVE LOGITS
     Rousse
    5.17
    Brazil
    3.75
     Brazilian
    3.72
     Brazil
    3.68
    ê
    3.35
     Bras
    3.34
     Dil
    3.31
    ça
    3.31
     Petro
    3.19
    ç
    3.09
    Activations Density 0.001%

    No Known Activations