© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 10509
    Prev
    Next
    INDEX
    Explanations

    references to potential collusion or interactions with Russian officials

    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
    0:0.19
    1:0.05
    2:0.08
    3:0.04
    4:0.04
    5:0.03
    6:0.10
    7:0.11
    8:0.04
    9:0.06
    10:0.15
    11:0.05
    Negative Logits
     Marshall
    -3.21
     Whitman
    -3.19
     AQ
    -3.13
     Straw
    -3.05
     backfield
    -3.02
     MAC
    -2.89
    Mu
    -2.88
     poem
    -2.85
     CLR
    -2.84
    bean
    -2.83
    POSITIVE LOGITS
     Ves
    9.30
     Kats
    4.47
     Vas
    4.41
     Ples
    4.37
     Kislyak
    4.11
     Gors
    4.01
    Magn
    4.00
     Kes
    3.94
     Vec
    3.92
     Sev
    3.89
    Activations Density 0.002%

    No Known Activations