© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 10819
    Prev
    Next
    INDEX
    Explanations

    phrases related to risk and danger

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.04
    1:0.03
    2:0.02
    3:0.04
    4:0.05
    5:0.04
    6:0.03
    7:0.04
    8:0.02
    9:0.17
    10:0.03
    11:0.45
    Negative Logits
     avail
    -2.35
     applications
    -2.29
    Events
    -2.27
     instances
    -2.19
     combinations
    -2.18
     edition
    -2.15
     editions
    -2.14
     contexts
    -2.11
     cases
    -2.10
     listings
    -2.10
    POSITIVE LOGITS
    Step
    3.09
    walk
    3.01
     steps
    2.95
    steps
    2.88
     Step
    2.84
    path
    2.81
    step
    2.72
     Steps
    2.70
     path
    2.62
     stride
    2.58
    Activations Density 0.003%

    No Known Activations