© 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. 10-ATT-KK
    11. 15410
    Prev
    Next
    INDEX
    Explanations

    statements related to events and their details

    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
    0:0.20
    1:0.11
    2:0.07
    3:0.07
    4:0.03
    5:0.02
    6:0.08
    7:0.09
    8:0.01
    9:0.03
    10:0.19
    11:0.06
    Negative Logits
    dh
    -3.79
    DK
    -3.45
     Hatt
    -3.30
     wip
    -3.26
    Iv
    -3.24
     Spielberg
    -3.23
     Deng
    -3.18
     bab
    -3.16
    DH
    -3.10
     Brill
    -3.01
    POSITIVE LOGITS
     Terra
    9.76
     Aqua
    5.16
    Mars
    4.51
    Ter
    4.23
     Mars
    4.11
     Vent
    3.91
     ter
    3.87
     Gaia
    3.70
     Nova
    3.65
     Uran
    3.62
    Activations Density 0.001%

    No Known Activations