© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 15854
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate scams, legal matters, and formal interactions

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    0:0.05
    1:0.03
    2:0.28
    3:0.04
    4:0.06
    5:0.12
    6:0.02
    7:0.03
    8:0.08
    9:0.16
    10:0.05
    11:0.02
    Negative Logits
    doms
    -1.26
     magnification
    -1.17
    Circ
    -1.17
    Cause
    -1.16
     mot
    -1.16
    kernel
    -1.15
    Analysis
    -1.11
    Offline
    -1.11
    aminer
    -1.11
     coord
    -1.10
    POSITIVE LOGITS
    ouf
    1.38
    illin
    1.34
    endment
    1.32
    urate
    1.30
    ouk
    1.29
    urat
    1.26
     Lah
    1.26
    opol
    1.26
    ala
    1.25
    uku
    1.24
    Activations Density 0.044%

    No Known Activations