© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 20075
    Prev
    Next
    INDEX
    Explanations

    references to offshore financial practices and their implications

    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
    0:0.15
    1:0.02
    2:0.21
    3:0.10
    4:0.03
    5:0.09
    6:0.05
    7:0.06
    8:0.13
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
     Pryor
    -2.70
     Pediatrics
    -2.67
     Pyro
    -2.66
    Dur
    -2.61
     Slay
    -2.60
     Injury
    -2.51
    Battery
    -2.47
     Pistol
    -2.46
     Bullets
    -2.45
     TAMADRA
    -2.44
    POSITIVE LOGITS
     offshore
    6.34
     Bermuda
    5.24
     havens
    4.96
     Luxembourg
    4.60
     HSBC
    4.49
     Bahamas
    4.45
     Panama
    4.27
     Cay
    4.26
     laundering
    4.08
    shore
    4.06
    Activations Density 0.070%

    No Known Activations