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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 9398
    Prev
    Next
    INDEX
    Explanations

    phrases and vocabulary related to decision-making and choices in a context of trade-offs

    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
    0:0.16
    1:0.15
    2:0.05
    3:0.04
    4:0.03
    5:0.04
    6:0.06
    7:0.09
    8:0.04
    9:0.03
    10:0.21
    11:0.05
    Negative Logits
     Glover
    -3.63
     Bagg
    -3.33
     Raven
    -3.23
    moon
    -3.09
     Tracy
    -3.08
     Coff
    -2.94
    brown
    -2.92
     Tempest
    -2.82
     Bat
    -2.81
     Marty
    -2.77
    POSITIVE LOGITS
     Sek
    6.88
     Nek
    4.58
    ek
    4.42
     Dek
    4.25
     Kes
    4.16
     Ek
    4.02
     Tek
    3.93
     Mek
    3.79
     Uk
    3.68
     Kik
    3.56
    Activations Density 0.000%

    No Known Activations