© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 7026
    Prev
    Next
    INDEX
    Explanations

    references to historical nuclear disasters and their consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.26
    1:0.04
    2:0.04
    3:0.07
    4:0.05
    5:0.02
    6:0.07
    7:0.16
    8:0.01
    9:0.06
    10:0.09
    11:0.07
    Negative Logits
     Ellison
    -3.91
     Palmer
    -3.12
    Ell
    -3.03
     Pell
    -2.95
     Abedin
    -2.85
     cookie
    -2.81
     Jasper
    -2.80
    acus
    -2.78
     Quentin
    -2.77
     Porter
    -2.74
    POSITIVE LOGITS
    obyl
    7.80
     Chern
    6.47
     Fukushima
    5.49
     Ukrainians
    4.77
     radioactive
    4.55
     Belarus
    4.48
    Ukraine
    4.46
     reactor
    4.45
     Ukraine
    4.43
     Ukrainian
    4.35
    Activations Density 0.005%

    No Known Activations