© 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. 12823
    Prev
    Next
    INDEX
    Explanations

    terms related to crisis situations

    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
    0:0.07
    1:0.03
    2:0.10
    3:0.21
    4:0.07
    5:0.13
    6:0.01
    7:0.10
    8:0.06
    9:0.01
    10:0.12
    11:0.03
    Negative Logits
    nesday
    -2.30
    statement
    -2.13
    laughter
    -2.11
    udeb
    -2.03
    ticket
    -2.01
    )))
    -2.00
    utils
    -1.94
    endment
    -1.89
    mination
    -1.88
    aturday
    -1.85
    POSITIVE LOGITS
     uncover
    2.80
     Enemies
    2.67
     perilous
    2.65
     fearsome
    2.59
     quests
    2.56
     mysteries
    2.51
     puzzles
    2.46
     cunning
    2.43
     deadly
    2.43
     journeys
    2.38
    Activations Density 0.523%

    No Known Activations