© 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 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. 20752
    Prev
    Next
    INDEX
    Explanations

    inquiries or questions concerning the Department of Energy's targets and achievements

    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
    0:0.15
    1:0.05
    2:0.09
    3:0.04
    4:0.05
    5:0.04
    6:0.15
    7:0.11
    8:0.03
    9:0.06
    10:0.13
    11:0.05
    Negative Logits
     Sven
    -3.93
    76561
    -3.59
     Sask
    -3.43
     Canucks
    -3.25
    ð
    -3.13
     Manitoba
    -3.10
     Winnipeg
    -2.99
    Pir
    -2.98
    �
    -2.96
     Bj
    -2.95
    POSITIVE LOGITS
     DOE
    7.82
    DO
    5.87
     DOI
    4.01
     DOD
    3.60
     Doomsday
    3.48
     DOT
    3.44
     DO
    3.39
     plutonium
    3.39
     DOJ
    3.30
    Energy
    3.19
    Activations Density 0.001%

    No Known Activations