© 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. 22795
    Prev
    Next
    INDEX
    Explanations

    references to significant financial scandals involving high-profile individuals and organizations

    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
    0:0.19
    1:0.01
    2:0.24
    3:0.07
    4:0.02
    5:0.10
    6:0.03
    7:0.04
    8:0.17
    9:0.02
    10:0.03
    11:0.02
    Negative Logits
     Archdemon
    -2.96
    Alert
    -2.79
    arantine
    -2.69
    ombat
    -2.67
     Horde
    -2.50
    ggies
    -2.48
    fork
    -2.48
     Slay
    -2.47
     Stronghold
    -2.47
    �
    -2.44
    POSITIVE LOGITS
     offshore
    3.52
     riches
    3.44
     Panama
    3.39
     HSBC
    3.29
     billionaires
    3.25
     Transparency
    3.25
     tabloid
    3.12
     accountant
    3.11
     laundering
    3.01
     Luxembourg
    3.01
    Activations Density 0.014%

    No Known Activations