© 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. 15388
    Prev
    Next
    INDEX
    Explanations

    references to doors and their states (such as open or closed)

    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
    0:0.03
    1:0.03
    2:0.04
    3:0.05
    4:0.06
    5:0.16
    6:0.03
    7:0.10
    8:0.03
    9:0.34
    10:0.02
    11:0.04
    Negative Logits
     equals
    -2.25
    levels
    -2.21
     comparable
    -2.16
    Redd
    -1.99
     Lv
    -1.95
    soDeliveryDate
    -1.91
     worldwide
    -1.87
     INCLUD
    -1.85
     Glob
    -1.85
     ranges
    -1.83
    POSITIVE LOGITS
    gently
    2.18
     shut
    2.10
     softly
    2.06
     Spicer
    1.98
    usercontent
    1.97
     Rasmussen
    1.96
    ��
    1.94
     UID
    1.93
     silently
    1.93
     appellant
    1.89
    Activations Density 0.003%

    No Known Activations