© 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. 10879
    Prev
    Next
    INDEX
    Explanations

    phrases related to government actions and budgeting for infrastructure and transportation

    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
    0:0.18
    1:0.10
    2:0.03
    3:0.05
    4:0.05
    5:0.02
    6:0.08
    7:0.19
    8:0.02
    9:0.03
    10:0.10
    11:0.08
    Negative Logits
     Zoro
    -3.04
     Psychic
    -2.80
     exorc
    -2.66
     transsexual
    -2.65
    Psych
    -2.64
     Barbar
    -2.63
     psychic
    -2.50
     witches
    -2.41
     Psycho
    -2.41
     occult
    -2.39
    POSITIVE LOGITS
     congestion
    4.46
     congest
    3.58
     freeway
    2.90
    queue
    2.83
    iard
    2.62
     jams
    2.55
    Lot
    2.51
    cong
    2.48
     roads
    2.46
     highways
    2.45
    Activations Density 0.001%

    No Known Activations