© 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. 22915
    Prev
    Next
    INDEX
    Explanations

    terms relating to regulatory actions and safety warnings from the FDA

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

    No Comments

    Head Attr Weights
    0:0.16
    1:0.04
    2:0.06
    3:0.06
    4:0.09
    5:0.03
    6:0.19
    7:0.12
    8:0.02
    9:0.05
    10:0.08
    11:0.05
    Negative Logits
     Strongh
    -3.11
     hangar
    -2.68
     chau
    -2.68
     Cardiff
    -2.64
     prolet
    -2.63
     secession
    -2.50
     Warp
    -2.47
     organising
    -2.46
     Tel
    -2.45
     Wales
    -2.44
    POSITIVE LOGITS
     FDA
    7.14
     FTC
    4.60
     DEA
    3.96
     pharm
    3.55
     NIH
    3.49
     regulators
    3.43
     CDC
    3.42
     regulatory
    3.41
     prescribing
    3.39
     pediatric
    3.37
    Activations Density 0.022%

    No Known Activations