© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 20166
    Prev
    Next
    INDEX
    Explanations

    references to intelligence agencies and their operations

    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
    0:0.27
    1:0.01
    2:0.19
    3:0.10
    4:0.02
    5:0.10
    6:0.03
    7:0.04
    8:0.08
    9:0.04
    10:0.04
    11:0.02
    Negative Logits
     wheelchair
    -2.74
     Rubber
    -2.70
     Parking
    -2.47
    phalt
    -2.37
     dentist
    -2.35
     asphalt
    -2.33
     Merch
    -2.30
     bicycl
    -2.30
     debtor
    -2.26
     abolition
    -2.24
    POSITIVE LOGITS
    elligence
    5.38
     intelligence
    5.21
     Intelligence
    5.04
    intelligence
    4.41
     intel
    4.38
     spy
    4.17
     Clapper
    4.05
     spies
    3.96
     spying
    3.85
     espionage
    3.68
    Activations Density 0.059%

    No Known Activations