© 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. 23293
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety and risk management

    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
    0:0.06
    1:0.33
    2:0.05
    3:0.16
    4:0.04
    5:0.02
    6:0.05
    7:0.08
    8:0.02
    9:0.03
    10:0.08
    11:0.03
    Negative Logits
     Hoo
    -2.59
    oshenko
    -2.59
    inda
    -2.43
    itiveness
    -2.38
    ilater
    -2.31
    FORE
    -2.30
    eno
    -2.27
     inclusive
    -2.25
    chwitz
    -2.24
    viron
    -2.23
    POSITIVE LOGITS
     Fall
    6.49
     fall
    6.46
    fall
    6.17
     Falling
    6.12
    Fall
    5.70
     fallen
    5.34
     falls
    5.29
     fell
    5.15
     falling
    5.11
     Fallen
    4.81
    Activations Density 0.071%

    No Known Activations