© 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. 11996
    Prev
    Next
    INDEX
    Explanations

    financial metrics and information related to oil production and market trends

    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
    0:0.44
    1:0.04
    2:0.02
    3:0.05
    4:0.05
    5:0.02
    6:0.07
    7:0.07
    8:0.01
    9:0.05
    10:0.05
    11:0.08
    Negative Logits
    Pokémon
    -4.70
     Pokémon
    -4.43
     Scarlet
    -4.14
     Daredevil
    -4.03
     Cic
    -3.98
     Pikachu
    -3.96
     Droid
    -3.95
     Hung
    -3.89
     Mei
    -3.84
     Vacc
    -3.84
    POSITIVE LOGITS
    Oil
    9.08
     oil
    8.60
     Oil
    8.58
     Petroleum
    8.36
     OPEC
    8.13
     petroleum
    7.88
     drilling
    7.33
     Exxon
    7.28
     shale
    7.18
    oil
    6.99
    Activations Density 0.553%

    No Known Activations