© 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. 5-ATT-KK
    11. 21789
    Prev
    Next
    INDEX
    Explanations

    phrases related to dishonesty or deception

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.06
    3:0.05
    4:0.10
    5:0.03
    6:0.05
    7:0.46
    8:0.03
    9:0.03
    10:0.07
    11:0.06
    Negative Logits
    wcs
    -1.78
    jee
    -1.50
     guiActiveUnfocused
    -1.49
    uel
    -1.47
    ONSORED
    -1.44
     mell
    -1.44
    rontal
    -1.39
    ULAR
    -1.38
     trending
    -1.36
     bustling
    -1.36
    POSITIVE LOGITS
     omission
    2.14
     perjury
    1.72
     conceal
    1.63
     accusation
    1.60
     accus
    1.55
     denying
    1.55
     faked
    1.55
     liar
    1.54
     witnesses
    1.51
     deny
    1.50
    Activations Density 0.013%

    No Known Activations