© 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. 21919
    Prev
    Next
    INDEX
    Explanations

    terms related to classified information and governmental procedures

    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
    0:0.08
    1:0.06
    2:0.09
    3:0.06
    4:0.08
    5:0.08
    6:0.15
    7:0.08
    8:0.04
    9:0.09
    10:0.05
    11:0.10
    Negative Logits
    onga
    -3.07
     healthier
    -2.76
    lander
    -2.73
     wont
    -2.72
    urable
    -2.69
     champ
    -2.65
     starter
    -2.50
     rud
    -2.42
     champion
    -2.42
     toast
    -2.41
    POSITIVE LOGITS
    FBI
    5.01
    CIA
    4.71
     FBI
    4.64
     CIA
    4.50
     FOIA
    4.42
     declass
    4.33
     DOJ
    4.25
     NSA
    4.24
     DOD
    4.12
    Documents
    4.05
    Activations Density 0.159%

    No Known Activations