© 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. 5-ATT-KK
    11. 27978
    Prev
    Next
    INDEX
    Explanations

    phrases indicating prevention or avoidance of negative outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.07
    3:0.08
    4:0.28
    5:0.02
    6:0.03
    7:0.25
    8:0.03
    9:0.03
    10:0.05
    11:0.07
    Negative Logits
    AppData
    -1.80
    cloth
    -1.73
    onyms
    -1.57
    database
    -1.56
    ebook
    -1.53
     Yaz
    -1.44
     Kardash
    -1.43
     Palest
    -1.43
     Qur
    -1.41
     Quran
    -1.40
    POSITIVE LOGITS
     hostilities
    1.95
     deterioration
    1.88
     overload
    1.87
     inevitable
    1.87
     failure
    1.85
     impending
    1.83
     revolt
    1.82
     erosion
    1.78
     disruption
    1.77
     backlash
    1.71
    Activations Density 0.000%

    No Known Activations