© 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. 9123
    Prev
    Next
    INDEX
    Explanations

    references to nuclear incidents and their consequences

    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
    0:0.13
    1:0.02
    2:0.17
    3:0.07
    4:0.04
    5:0.11
    6:0.05
    7:0.05
    8:0.22
    9:0.04
    10:0.03
    11:0.03
    Negative Logits
    ̶
    -3.53
     Ellison
    -2.85
    Atlanta
    -2.69
     Bacon
    -2.64
     Lamar
    -2.63
     Beyon
    -2.63
     negro
    -2.62
     Lyn
    -2.60
     Negro
    -2.57
    ACP
    -2.53
    POSITIVE LOGITS
     Fukushima
    6.77
     reactors
    4.73
     reactor
    4.62
     radioactive
    4.46
     tsunami
    4.46
     radiation
    4.45
     Dai
    4.38
    ushima
    4.26
     nuclear
    4.04
     Radiation
    4.04
    Activations Density 0.032%

    No Known Activations