© 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. 5716
    Prev
    Next
    INDEX
    Explanations

    instances of dialogue or quoted speech

    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
    0:0.09
    1:0.03
    2:0.07
    3:0.03
    4:0.05
    5:0.04
    6:0.28
    7:0.04
    8:0.06
    9:0.20
    10:0.02
    11:0.05
    Negative Logits
     Warriors
    -3.71
     Nanto
    -3.64
     apes
    -3.57
     Conan
    -3.54
     Russo
    -3.52
    isite
    -3.41
     Portuguese
    -3.33
    ��
    -3.31
    995
    -3.28
    STEP
    -3.25
    POSITIVE LOGITS
     Holl
    8.63
     Ell
    8.58
     Boll
    5.99
     Mell
    5.85
     ell
    5.67
    oll
    5.12
    Ell
    4.88
     Loll
    4.35
     Doll
    4.18
     Mull
    4.18
    Activations Density 0.004%

    No Known Activations