© 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. 10-ATT-KK
    11. 6562
    Prev
    Next
    INDEX
    Explanations

    specific technical details and guidelines related to safety, health conditions, and medical practices

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.04
    1:0.05
    2:0.06
    3:0.05
    4:0.11
    5:0.32
    6:0.04
    7:0.06
    8:0.04
    9:0.09
    10:0.03
    11:0.05
    Negative Logits
     huh
    -2.95
     yesterday
    -2.87
     shockingly
    -2.86
     damn
    -2.85
     today
    -2.78
     lately
    -2.72
     amazingly
    -2.56
     unbelievably
    -2.52
    luaj
    -2.52
     damned
    -2.51
    POSITIVE LOGITS
     may
    4.71
     MUST
    4.37
     can
    4.23
    may
    4.21
    must
    4.15
     Alternatively
    4.11
     SHALL
    4.06
     cannot
    4.04
     must
    3.94
     MAY
    3.92
    Activations Density 0.614%

    No Known Activations