© 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. 6306
    Prev
    Next
    INDEX
    Explanations

    phrases related to digital access and subscriptions to newspapers or magazines

    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
    0:0.13
    1:0.04
    2:0.06
    3:0.25
    4:0.03
    5:0.18
    6:0.05
    7:0.04
    8:0.05
    9:0.03
    10:0.07
    11:0.03
    Negative Logits
     occupying
    -2.05
     backdrop
    -1.98
     orcs
    -1.94
     ribbon
    -1.91
    hang
    -1.89
    ihu
    -1.88
     occup
    -1.87
    urn
    -1.86
    kies
    -1.86
    oyer
    -1.83
    POSITIVE LOGITS
     Diabetes
    2.25
     Heat
    2.25
     predictive
    2.16
    Daily
    2.12
    Studies
    2.08
    angelo
    2.07
     forecasting
    2.02
     Diagn
    1.99
    Heat
    1.99
     workouts
    1.99
    Activations Density 0.002%

    No Known Activations