© 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. 9-ATT-KK
    11. 5730
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly dates and names associated with events or publications

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.16
    1:0.02
    2:0.03
    3:0.17
    4:0.03
    5:0.08
    6:0.02
    7:0.07
    8:0.08
    9:0.02
    10:0.22
    11:0.04
    Negative Logits
     competent
    -2.02
     talented
    -2.02
     skilled
    -1.93
     facilit
    -1.92
     decent
    -1.92
     inexperienced
    -1.91
     latent
    -1.90
     possibilities
    -1.89
     capable
    -1.89
     systems
    -1.86
    POSITIVE LOGITS
     Accessed
    2.81
     VIDEOS
    2.49
     Minutes
    2.39
     Retrieved
    2.31
     Interview
    2.29
     DOI
    2.28
    Daily
    2.27
     January
    2.21
    January
    2.19
     Citation
    2.19
    Activations Density 0.005%

    No Known Activations