© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 1269
    Prev
    Next
    INDEX
    Explanations

    phrases related to the effectiveness and attributes of single-payer health care systems

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.31
    1:0.01
    2:0.21
    3:0.09
    4:0.02
    5:0.10
    6:0.02
    7:0.05
    8:0.06
    9:0.02
    10:0.03
    11:0.03
    Negative Logits
    song
    -2.29
    Joined
    -2.28
     Ender
    -2.25
     crochet
    -2.25
    andom
    -2.24
    ilts
    -2.20
     Jeep
    -2.19
     Lego
    -2.19
     Brewing
    -2.16
     Interstellar
    -2.14
    POSITIVE LOGITS
     clinics
    3.83
     patients
    3.64
     providers
    3.63
     outpatient
    3.45
     patient
    3.44
     healthcare
    3.40
     NHS
    3.40
     hospitals
    3.22
     doctors
    3.20
     provider
    3.20
    Activations Density 0.110%

    No Known Activations