© 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. 2-ATT-KK
    11. 15934
    Prev
    Next
    INDEX
    Explanations

    words related to Medicare and health care policies

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.05
    1:0.03
    2:0.19
    3:0.08
    4:0.11
    5:0.06
    6:0.03
    7:0.05
    8:0.04
    9:0.23
    10:0.07
    11:0.03
    Negative Logits
    bek
    -1.62
    asp
    -1.40
    rano
    -1.38
    voy
    -1.36
    andowski
    -1.33
    atos
    -1.32
    aval
    -1.31
    ain
    -1.31
    anse
    -1.30
    rations
    -1.30
    POSITIVE LOGITS
     insured
    1.54
     Digest
    1.40
     uncond
    1.27
     Guarant
    1.23
     Regulations
    1.20
     Registered
    1.17
    iatrics
    1.14
     suff
    1.12
     growers
    1.11
     Medicaid
    1.11
    Activations Density 0.007%

    No Known Activations