© 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. 14425
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names

    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
    0:0.10
    1:0.27
    2:0.04
    3:0.06
    4:0.04
    5:0.02
    6:0.07
    7:0.11
    8:0.03
    9:0.03
    10:0.13
    11:0.06
    Negative Logits
     mul
    -3.00
     tur
    -2.81
     Mul
    -2.79
     Dil
    -2.77
     exorc
    -2.69
    uyomi
    -2.61
     Pur
    -2.59
     subdu
    -2.54
     Byr
    -2.53
     Ver
    -2.48
    POSITIVE LOGITS
    ost
    3.41
    oeuv
    3.07
     Ost
    2.96
    ust
    2.94
    orst
    2.89
    est
    2.75
    hest
    2.73
    lov
    2.72
    OST
    2.71
    arth
    2.68
    Activations Density 0.005%

    No Known Activations