© 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. 3-ATT-KK
    6. 7996
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to federal regulations and policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.11
    3:0.04
    4:0.03
    5:0.04
    6:0.33
    7:0.14
    8:0.03
    9:0.02
    10:0.08
    11:0.07
    Negative Logits
    byn
    -1.47
     Malk
    -1.27
    rang
    -1.22
     Kik
    -1.21
    BuyableInstoreAndOnline
    -1.17
     Schl
    -1.14
    Putin
    -1.09
     Sharks
    -1.08
     Penguins
    -1.07
     Yose
    -1.06
    POSITIVE LOGITS
     agencies
    1.31
    forcement
    1.26
     Publication
    1.25
     jurisdiction
    1.22
     treaties
    1.21
     oversight
    1.18
    reach
    1.16
     inspectors
    1.16
     funding
    1.15
     guidelines
    1.14
    Activations Density 0.081%

    No Known Activations