© 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. 10-ATT-KK
    11. 12216
    Prev
    Next
    INDEX
    Explanations

    instances of deception or falsehood, particularly in relation to individuals and their credibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.11
    2:0.06
    3:0.05
    4:0.15
    5:0.03
    6:0.10
    7:0.09
    8:0.02
    9:0.04
    10:0.13
    11:0.10
    Negative Logits
    TPS
    -2.66
     Cham
    -2.62
    peed
    -2.50
     Mog
    -2.49
     Scarlet
    -2.37
    ighth
    -2.37
     Generations
    -2.31
    EMP
    -2.30
    avorite
    -2.27
    Vision
    -2.26
    POSITIVE LOGITS
     lie
    6.37
     lying
    6.03
     liar
    5.96
     lies
    5.53
     lied
    5.44
     Lie
    5.20
     li
    4.96
     Lies
    4.96
    Lie
    4.75
     perjury
    4.37
    Activations Density 0.013%

    No Known Activations