© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 7765
    Prev
    Next
    INDEX
    Explanations

    mentions of the Food and Drug Administration (FDA) and related regulatory actions

    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
    0:0.23
    1:0.04
    2:0.18
    3:0.11
    4:0.03
    5:0.08
    6:0.04
    7:0.06
    8:0.05
    9:0.04
    10:0.04
    11:0.04
    Negative Logits
     graduates
    -3.02
     decom
    -3.00
     classrooms
    -2.82
     coh
    -2.75
     anchored
    -2.73
     nesting
    -2.68
     nests
    -2.65
     civic
    -2.62
     hull
    -2.61
     graduate
    -2.59
    POSITIVE LOGITS
     Devices
    2.76
     FDA
    2.73
     approving
    2.66
     Desire
    2.64
     Regulatory
    2.58
    appro
    2.58
     testers
    2.57
     Device
    2.42
     Turing
    2.34
     approval
    2.29
    Activations Density 0.002%

    No Known Activations