Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 84
    Prev
    Next
    INDEX
    Explanations

    references to health safety protocols related to injections and pharmaceuticals

    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
    0:0.12
    1:0.03
    2:0.14
    3:0.05
    4:0.04
    5:0.04
    6:0.16
    7:0.06
    8:0.04
    9:0.21
    10:0.04
    11:0.03
    Negative Logits
     Ky
    -3.98
     Kru
    -3.82
     Thur
    -3.70
     Ukrain
    -3.68
    �
    -3.58
     forests
    -3.54
    aru
    -3.50
    �
    -3.49
     calendars
    -3.48
     Chero
    -3.48
    POSITIVE LOGITS
     inject
    7.55
     injected
    7.29
     injection
    7.28
     injecting
    7.24
     implant
    6.80
     injections
    6.52
     implants
    5.57
     Insert
    5.42
     implanted
    5.39
    Insert
    5.30
    Activations Density 0.005%

    No Known Activations