© 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. 5-ATT-KK
    11. 47218
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce questions or call attention to topics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.10
    3:0.11
    4:0.25
    5:0.04
    6:0.05
    7:0.16
    8:0.04
    9:0.04
    10:0.06
    11:0.06
    Negative Logits
     awarding
    -1.78
     destro
    -1.78
     adversely
    -1.60
     hesitated
    -1.57
     impacted
    -1.54
    iership
    -1.51
     challeng
    -1.50
     declare
    -1.47
     jumped
    -1.44
    edin
    -1.42
    POSITIVE LOGITS
     Grave
    1.62
     Cave
    1.50
    lite
    1.50
    Dog
    1.49
     Supplementary
    1.47
     Ghosts
    1.46
    Alias
    1.40
     Saber
    1.37
     Dogs
    1.37
    Mut
    1.36
    Activations Density 0.004%

    No Known Activations