© 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. 12679
    Prev
    Next
    INDEX
    Explanations

    objects and actions involved in high-stress situations or conflicts

    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
    0:0.04
    1:0.02
    2:0.06
    3:0.12
    4:0.01
    5:0.08
    6:0.02
    7:0.06
    8:0.02
    9:0.01
    10:0.49
    11:0.01
    Negative Logits
     Concern
    -2.61
     concern
    -2.59
     caution
    -2.36
    anger
    -2.21
    cern
    -2.20
     Suggest
    -2.19
     worry
    -2.18
     worries
    -2.16
     beware
    -2.14
     worrying
    -2.10
    POSITIVE LOGITS
     successfully
    3.54
    successfully
    3.16
     safely
    2.95
     efficiently
    2.91
     convinc
    2.80
     undet
    2.80
     survived
    2.70
     survive
    2.60
     sufficiently
    2.58
     satisf
    2.57
    Activations Density 0.540%

    No Known Activations