© 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. 2-ATT-KK
    11. 11416
    Prev
    Next
    INDEX
    Explanations

    references to economic entities and activities

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.05
    1:0.24
    2:0.03
    3:0.05
    4:0.02
    5:0.04
    6:0.07
    7:0.11
    8:0.04
    9:0.06
    10:0.16
    11:0.08
    Negative Logits
    REDACTED
    -2.22
     prank
    -2.08
     nudity
    -2.06
    RAW
    -1.99
     incrim
    -1.98
     blaster
    -1.96
     misc
    -1.93
     nude
    -1.91
     cheek
    -1.84
    Trigger
    -1.82
    POSITIVE LOGITS
     economists
    2.86
     Econom
    2.74
     economically
    2.66
     economic
    2.63
    Economic
    2.61
     economies
    2.60
    econom
    2.60
     economist
    2.56
     OECD
    2.51
    economic
    2.50
    Activations Density 0.901%

    No Known Activations