© 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. 17276
    Prev
    Next
    INDEX
    Explanations

    mentions of medical or health-related topics, particularly those associated with diabetes and insulin regulation

    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
    0:0.02
    1:0.02
    2:0.03
    3:0.03
    4:0.04
    5:0.14
    6:0.02
    7:0.03
    8:0.02
    9:0.48
    10:0.01
    11:0.10
    Negative Logits
    iths
    -3.06
    azes
    -2.96
    pieces
    -2.90
    renches
    -2.90
    osaurs
    -2.89
    esters
    -2.88
    bats
    -2.88
    leys
    -2.85
    icons
    -2.79
    casts
    -2.78
    POSITIVE LOGITS
     designation
    2.94
     option
    2.72
     requirement
    2.58
     berth
    2.53
     scenario
    2.49
     arrangement
    2.48
     recommendation
    2.44
     clause
    2.43
     somewhere
    2.40
     consisting
    2.40
    Activations Density 1.166%

    No Known Activations