Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44185
    Prev
    Next
    INDEX
    Explanations

    terminology related to money laundering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.02
    2:0.06
    3:0.05
    4:0.13
    5:0.04
    6:0.03
    7:0.32
    8:0.04
    9:0.05
    10:0.11
    11:0.09
    Negative Logits
    zai
    -1.56
    tained
    -1.36
    cho
    -1.33
    amous
    -1.23
    mouth
    -1.22
    leck
    -1.20
    ppa
    -1.18
    lymp
    -1.17
    mand
    -1.16
    ewitness
    -1.16
    POSITIVE LOGITS
    avorite
    1.25
    aunder
    1.25
    OUP
    1.22
     euros
    1.19
    Ts
    1.18
    afort
    1.18
     borrowed
    1.16
     merchandise
    1.16
     Rs
    1.15
     Orig
    1.15
    Activations Density 0.001%

    No Known Activations