© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 3110
    Prev
    Next
    INDEX
    Explanations

    activities and actions that indicate urgency or critical situations

    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
    0:0.03
    1:0.02
    2:0.16
    3:0.23
    4:0.16
    5:0.03
    6:0.04
    7:0.06
    8:0.05
    9:0.04
    10:0.06
    11:0.06
    Negative Logits
    udos
    -1.98
    itivity
    -1.73
    Wide
    -1.71
    verages
    -1.65
    enza
    -1.64
    ciplinary
    -1.58
    ISION
    -1.50
    enne
    -1.50
    enum
    -1.49
    laus
    -1.47
    POSITIVE LOGITS
     or
    2.01
     newsp
    1.76
    cknow
    1.60
     etc
    1.59
    ?,
    1.54
     →
    1.46
     yourself
    1.44
     nor
    1.44
     XY
    1.43
     OR
    1.42
    Activations Density 0.063%

    No Known Activations