© 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. 13923
    Prev
    Next
    INDEX
    Explanations

    informal expressions or transitions used in conversation

    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
    0:0.11
    1:0.08
    2:0.06
    3:0.05
    4:0.04
    5:0.04
    6:0.12
    7:0.06
    8:0.03
    9:0.05
    10:0.21
    11:0.08
    Negative Logits
     bel
    -3.63
     Mil
    -3.09
     hol
    -3.01
     Pl
    -2.96
     prof
    -2.87
     Bel
    -2.80
    Bel
    -2.77
     Pol
    -2.73
     Walt
    -2.73
     Conc
    -2.61
    POSITIVE LOGITS
     Rag
    8.97
    rag
    6.08
     rag
    6.04
     Ran
    4.61
     Raz
    4.31
     Razor
    3.98
     Rak
    3.98
     Ras
    3.97
    RAG
    3.88
     Bag
    3.79
    Activations Density 0.000%

    No Known Activations