© 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. 8449
    Prev
    Next
    INDEX
    Explanations

    references to government policies and subsidies related to healthcare

    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
    0:0.19
    1:0.02
    2:0.20
    3:0.07
    4:0.05
    5:0.08
    6:0.08
    7:0.04
    8:0.06
    9:0.10
    10:0.03
    11:0.03
    Negative Logits
     Mori
    -3.54
     detectives
    -3.16
     detective
    -3.14
     Detective
    -3.13
     Arkham
    -3.08
     Middles
    -3.03
     Clockwork
    -3.01
     Murd
    -2.86
     coroner
    -2.85
     Stur
    -2.72
    POSITIVE LOGITS
     subsidies
    6.49
     subsidy
    6.39
     subsid
    4.93
     subsidized
    4.66
     rebate
    3.78
     incentives
    3.65
    benef
    3.31
     vouchers
    3.31
     incentive
    3.25
     renewable
    3.24
    Activations Density 0.010%

    No Known Activations