© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14222
    Prev
    Next
    INDEX
    Explanations

    phrases indicating statements or 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
    0:0.12
    1:0.10
    2:0.08
    3:0.12
    4:0.04
    5:0.03
    6:0.07
    7:0.11
    8:0.03
    9:0.04
    10:0.16
    11:0.05
    Negative Logits
    irie
    -2.92
    renheit
    -2.81
     Raz
    -2.76
     Rice
    -2.61
    orter
    -2.54
    avorite
    -2.50
    owder
    -2.47
     Kazakh
    -2.46
    DOS
    -2.46
    ��
    -2.45
    POSITIVE LOGITS
     Christ
    5.96
    Christ
    5.36
     CHRIST
    4.84
     christ
    4.30
    christ
    4.29
    church
    4.12
    Church
    3.61
     Christensen
    3.54
     Canterbury
    3.44
     Messiah
    3.35
    Activations Density 0.012%

    No Known Activations