© 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. 22695
    Prev
    Next
    INDEX
    Explanations

    references to the United States government and its actions

    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
    0:0.07
    1:0.02
    2:0.16
    3:0.23
    4:0.03
    5:0.09
    6:0.02
    7:0.07
    8:0.13
    9:0.02
    10:0.06
    11:0.05
    Negative Logits
     favourites
    -2.35
     councillors
    -2.31
     mould
    -2.16
     festive
    -2.12
     councillor
    -2.12
     colourful
    -2.09
     organis
    -2.08
     BMC
    -2.07
     evenings
    -2.04
     tender
    -2.03
    POSITIVE LOGITS
     CIA
    3.43
    CIA
    3.36
    NSA
    3.15
     Pentagon
    3.14
    FBI
    3.08
     DEA
    2.99
     Patriot
    2.89
     FBI
    2.88
     neocons
    2.85
    Obama
    2.84
    Activations Density 0.204%

    No Known Activations