© 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. 9-ATT-KK
    11. 8428
    Prev
    Next
    INDEX
    Explanations

    references to security incidents involving the Secret Service

    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
    0:0.11
    1:0.03
    2:0.21
    3:0.08
    4:0.03
    5:0.09
    6:0.06
    7:0.05
    8:0.16
    9:0.07
    10:0.03
    11:0.03
    Negative Logits
     mould
    -2.82
     dx
    -2.80
    conom
    -2.78
     GST
    -2.76
     delta
    -2.75
     regress
    -2.73
     flavours
    -2.71
    Benz
    -2.68
     litres
    -2.66
     CLR
    -2.66
    POSITIVE LOGITS
     Secret
    6.14
    Secret
    5.28
     Homeland
    4.10
    secret
    3.84
     Patriot
    3.69
    FBI
    3.67
     NYPD
    3.52
     TSA
    3.51
     FBI
    3.50
     DHS
    3.48
    Activations Density 0.008%

    No Known Activations