© 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. 2-ATT-KK
    11. 23080
    Prev
    Next
    INDEX
    Explanations

    information related to financial regulations and government oversight

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    mentions of regulatory issues and financial-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.06
    1:0.11
    2:0.07
    3:0.09
    4:0.02
    5:0.11
    6:0.09
    7:0.08
    8:0.08
    9:0.07
    10:0.12
    11:0.06
    Negative Logits
     glorious
    -1.39
     fucking
    -1.23
     fucked
    -1.22
     dreaded
    -1.15
     whore
    -1.14
     hero
    -1.12
     martyr
    -1.11
     wardrobe
    -1.11
     fuck
    -1.11
    ortal
    -1.09
    POSITIVE LOGITS
     DOE
    1.56
    Bloomberg
    1.50
    enegger
    1.46
    ESA
    1.44
    Reuters
    1.43
    quartered
    1.41
     Blasio
    1.38
    alyst
    1.33
    Companies
    1.32
    WASHINGTON
    1.31
    Activations Density 0.611%

    No Known Activations