© 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. 12773
    Prev
    Next
    INDEX
    Explanations

    phrases relating to orders or commands

    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
    0:0.05
    1:0.06
    2:0.06
    3:0.05
    4:0.05
    5:0.02
    6:0.37
    7:0.11
    8:0.03
    9:0.03
    10:0.04
    11:0.08
    Negative Logits
    David
    -2.53
    Camp
    -2.50
    enhagen
    -2.48
    Connell
    -2.34
     Gillespie
    -2.27
     Webb
    -2.26
    Walker
    -2.24
    Graham
    -2.24
     Walker
    -2.18
     David
    -2.17
    POSITIVE LOGITS
     orders
    8.15
     order
    7.76
     Order
    7.63
    Order
    7.63
     Orders
    7.42
    order
    7.24
    orders
    6.96
     ordering
    6.95
     ORDER
    6.58
     ordered
    6.38
    Activations Density 0.118%

    No Known Activations