© 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. 7931
    Prev
    Next
    INDEX
    Explanations

    adverbs and phrases indicating uncertainty or contrast

    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
    0:0.02
    1:0.01
    2:0.03
    3:0.03
    4:0.03
    5:0.08
    6:0.02
    7:0.03
    8:0.02
    9:0.64
    10:0.02
    11:0.03
    Negative Logits
    ilan
    -2.41
    estyles
    -2.26
    ivated
    -2.11
    ciating
    -1.94
    pire
    -1.92
    raits
    -1.90
    ois
    -1.82
    inguished
    -1.81
    ograp
    -1.80
    outed
    -1.79
    POSITIVE LOGITS
     that
    4.27
    that
    3.89
     THAT
    3.18
    That
    3.03
     That
    3.00
     thats
    1.97
     dat
    1.80
     those
    1.79
     tha
    1.63
     they
    1.62
    Activations Density 1.530%

    No Known Activations