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

    Neuronpedia

    APICircuit 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. 20681
    Prev
    Next
    INDEX
    Explanations

    information related to nuclear energy, its environmental impacts, and safety concerns

    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
    0:0.16
    1:0.01
    2:0.14
    3:0.09
    4:0.02
    5:0.07
    6:0.02
    7:0.05
    8:0.33
    9:0.02
    10:0.02
    11:0.02
    Negative Logits
    ̶
    -3.65
     Moroccan
    -3.09
     Clippers
    -3.04
     Hip
    -3.01
     Timberwolves
    -2.89
    inho
    -2.85
    Disney
    -2.83
    ç
    -2.81
     jQuery
    -2.80
    Uber
    -2.79
    POSITIVE LOGITS
     nuclear
    6.43
     plutonium
    6.28
    nuclear
    6.19
     reactors
    5.98
     Nuclear
    5.89
     reactor
    5.82
     uranium
    5.65
     Fukushima
    5.17
     radioactive
    5.10
     atomic
    5.06
    Activations Density 0.199%

    No Known Activations