© 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. 1381
    Prev
    Next
    INDEX
    Explanations

    indications of health-related risks and medical procedures

    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
    0:0.24
    1:0.03
    2:0.20
    3:0.07
    4:0.04
    5:0.09
    6:0.07
    7:0.05
    8:0.04
    9:0.07
    10:0.03
    11:0.02
    Negative Logits
    itect
    -3.26
     Architects
    -2.83
    1080
    -2.81
    itles
    -2.75
    ruct
    -2.64
     Bahrain
    -2.58
     Pixar
    -2.52
     Vall
    -2.48
     castles
    -2.43
    ottesville
    -2.42
    POSITIVE LOGITS
     needles
    6.68
     needle
    6.64
     HIV
    3.99
     sy
    3.90
     STD
    3.78
     heroin
    3.78
     injection
    3.71
     vein
    3.70
     AIDS
    3.61
     injecting
    3.58
    Activations Density 0.003%

    No Known Activations