© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 20262
    Prev
    Next
    INDEX
    Explanations

    discussions related to nuclear reactor construction and safety features

    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
    0:0.30
    1:0.01
    2:0.17
    3:0.09
    4:0.02
    5:0.12
    6:0.02
    7:0.05
    8:0.09
    9:0.02
    10:0.04
    11:0.01
    Negative Logits
     canv
    -2.88
     sneakers
    -2.88
     Shoes
    -2.70
     footwear
    -2.67
     Lyft
    -2.51
     Photoshop
    -2.47
     Dropbox
    -2.46
     Craigslist
    -2.40
     blurry
    -2.38
     blurred
    -2.36
    POSITIVE LOGITS
     reactors
    4.60
     reactor
    4.02
    uclear
    3.41
     Nuclear
    3.28
     Fukushima
    3.23
     uranium
    3.20
    nuclear
    3.18
     plutonium
    3.11
    utonium
    3.01
     nuclear
    2.98
    Activations Density 0.092%

    No Known Activations