© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 7879
    Prev
    Next
    INDEX
    Explanations

    phrases that express skepticism or doubt regarding a person's statements or 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
    0:0.19
    1:0.08
    2:0.07
    3:0.04
    4:0.03
    5:0.02
    6:0.15
    7:0.17
    8:0.01
    9:0.04
    10:0.08
    11:0.05
    Negative Logits
    ipeg
    -2.79
    zbollah
    -2.72
    oké
    -2.56
     flu
    -2.50
    pour
    -2.50
    oğ
    -2.48
     Dex
    -2.36
    mop
    -2.35
    án
    -2.33
     Sz
    -2.33
    POSITIVE LOGITS
     Roberts
    7.01
    Roberts
    6.37
     Robertson
    3.29
     Dodd
    2.67
    cru
    2.65
     Sith
    2.55
     Lawrence
    2.45
     Wesley
    2.44
     Roe
    2.42
     Hobby
    2.39
    Activations Density 0.014%

    No Known Activations