© 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. 9-ATT-KK
    11. 6337
    Prev
    Next
    INDEX
    Explanations

    phrases or expressions indicating surprise or emphasis

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.04
    1:0.09
    2:0.04
    3:0.17
    4:0.03
    5:0.05
    6:0.03
    7:0.03
    8:0.03
    9:0.03
    10:0.37
    11:0.03
    Negative Logits
     concurrently
    -2.34
    vernment
    -2.29
     despite
    -2.25
    76561
    -2.22
    vard
    -2.16
    despite
    -2.14
     spor
    -2.09
    Attempts
    -2.02
     toward
    -2.01
     casualty
    -2.01
    POSITIVE LOGITS
     marvelous
    2.38
     wonderful
    2.24
     GREAT
    2.21
    great
    2.20
     great
    2.13
     Lovely
    2.02
    Awesome
    2.01
     terrific
    2.01
     amazing
    1.96
     Awesome
    1.95
    Activations Density 0.028%

    No Known Activations