© 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. 23035
    Prev
    Next
    INDEX
    Explanations

    specific substances and terms related to liver regeneration and associated chemicals

    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
    0:0.10
    1:0.04
    2:0.03
    3:0.03
    4:0.07
    5:0.02
    6:0.04
    7:0.09
    8:0.02
    9:0.07
    10:0.03
    11:0.38
    Negative Logits
    aucuses
    -2.98
     openings
    -2.62
     ceilings
    -2.61
    yrights
    -2.50
     doors
    -2.46
    �
    -2.42
     achievements
    -2.38
     accomplishments
    -2.37
    selage
    -2.35
     gaping
    -2.32
    POSITIVE LOGITS
     substances
    4.26
     chemicals
    4.06
     medication
    4.05
     drugs
    4.01
     medications
    3.94
     aspirin
    3.87
     medicines
    3.87
     benz
    3.83
     analges
    3.82
     narc
    3.81
    Activations Density 0.465%

    No Known Activations