© 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. 9-ATT-KK
    11. 6759
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities related to investigations or legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.03
    2:0.11
    3:0.04
    4:0.07
    5:0.05
    6:0.12
    7:0.03
    8:0.11
    9:0.26
    10:0.02
    11:0.04
    Negative Logits
     Wynne
    -3.91
     tyre
    -3.61
     Kerry
    -3.55
     Wales
    -3.34
     rugby
    -3.33
     rice
    -3.27
    rider
    -3.23
     Welsh
    -3.09
     Roche
    -3.08
    chuk
    -3.07
    POSITIVE LOGITS
    FBI
    8.87
     FBI
    8.83
     ATF
    6.68
     Comey
    5.06
     Jihad
    4.82
     Bureau
    4.70
     bureau
    4.68
     Abedin
    4.52
     feds
    4.48
     Agents
    3.99
    Activations Density 0.013%

    No Known Activations