© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-ATT-KK
    11. 12904
    Prev
    Next
    INDEX
    Explanations

    phrases indicating skepticism or doubt, particularly regarding claims or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.10
    1:0.02
    2:0.08
    3:0.03
    4:0.04
    5:0.03
    6:0.24
    7:0.03
    8:0.05
    9:0.29
    10:0.02
    11:0.02
    Negative Logits
     Bridges
    -4.01
     Abbas
    -3.77
     Haas
    -3.60
    Palest
    -3.55
     Conver
    -3.53
     Alma
    -3.50
    Marx
    -3.40
     Faust
    -3.35
     Mao
    -3.32
     GF
    -3.31
    POSITIVE LOGITS
    Sn
    9.79
     Sn
    9.72
    sn
    9.11
     sn
    7.52
     snail
    6.46
    Snake
    6.36
    SN
    6.27
     SN
    5.96
     Snape
    5.67
     Sno
    5.63
    Activations Density 0.010%

    No Known Activations