© 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. 10-ATT-KK
    11. 13960
    Prev
    Next
    INDEX
    Explanations

    references to threats or dangers

    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
    0:0.03
    1:0.03
    2:0.03
    3:0.04
    4:0.09
    5:0.07
    6:0.03
    7:0.06
    8:0.02
    9:0.10
    10:0.02
    11:0.41
    Negative Logits
     routines
    -2.98
     traditions
    -2.96
     practices
    -2.83
     habits
    -2.75
     segments
    -2.73
     procedures
    -2.72
     sections
    -2.69
     Seasons
    -2.69
     methods
    -2.67
     ceremonies
    -2.63
    POSITIVE LOGITS
     threat
    3.38
     menace
    3.00
     danger
    2.95
     imminent
    2.86
     looming
    2.86
     prospect
    2.79
    threat
    2.73
     daunting
    2.66
    osate
    2.63
     posed
    2.47
    Activations Density 0.088%

    No Known Activations