© 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. 39487
    Prev
    Next
    INDEX
    Explanations

    verbs indicating regulation, imposition, and encouragement of actions or policies

    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
    0:0.09
    1:0.01
    2:0.32
    3:0.07
    4:0.07
    5:0.02
    6:0.04
    7:0.03
    8:0.09
    9:0.07
    10:0.08
    11:0.05
    Negative Logits
     selves
    -1.72
    EStream
    -1.69
     tending
    -1.57
     cov
    -1.55
    ��
    -1.54
     predicament
    -1.51
     mortal
    -1.44
    hari
    -1.44
     Situation
    -1.43
    joice
    -1.41
    POSITIVE LOGITS
     itself
    1.67
    izes
    1.64
     emphasizes
    1.48
     its
    1.48
    698
    1.47
     emphasis
    1.46
     depicts
    1.44
     incorporates
    1.44
    Output
    1.44
    701
    1.42
    Activations Density 0.334%

    No Known Activations