© 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. 5718
    Prev
    Next
    INDEX
    Explanations

    sentences that end with periods, particularly noting the word "Jess" and its variations

    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
    0:0.08
    1:0.03
    2:0.08
    3:0.04
    4:0.05
    5:0.05
    6:0.15
    7:0.05
    8:0.09
    9:0.27
    10:0.02
    11:0.02
    Negative Logits
     Fir
    -4.13
     Forth
    -3.94
     Okin
    -3.79
     Fo
    -3.75
    plant
    -3.51
    aird
    -3.51
    obyl
    -3.46
    ゴン
    -3.43
    ファ
    -3.42
     Potato
    -3.38
    POSITIVE LOGITS
     Jesse
    9.59
    Jes
    8.84
    Jess
    5.13
     Jessie
    5.12
     Jes
    4.83
     Saul
    4.49
     Walt
    4.35
     Jackson
    4.10
     Missouri
    3.94
     Jess
    3.90
    Activations Density 0.001%

    No Known Activations