© 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. 15219
    Prev
    Next
    INDEX
    Explanations

    quotations and reported speech

    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
    0:0.17
    1:0.14
    2:0.07
    3:0.06
    4:0.03
    5:0.03
    6:0.07
    7:0.07
    8:0.02
    9:0.04
    10:0.18
    11:0.04
    Negative Logits
    Turkish
    -3.49
    Cook
    -3.41
    ��
    -3.34
    Turkey
    -3.21
     Li
    -3.07
    acus
    -3.01
     Ankara
    -2.95
    Ruby
    -2.91
     CAL
    -2.89
     Turks
    -2.87
    POSITIVE LOGITS
     Hend
    10.06
     Henderson
    5.41
    hend
    4.31
     Hert
    4.25
     Hendricks
    4.07
     Hed
    3.96
     Hen
    3.88
     Hind
    3.73
     Hast
    3.65
     Ket
    3.62
    Activations Density 0.001%

    No Known Activations