© 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. 5-ATT-KK
    11. 10258
    Prev
    Next
    INDEX
    Explanations

    references to accountability and moral responsibility

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.12
    1:0.31
    2:0.03
    3:0.02
    4:0.03
    5:0.20
    6:0.03
    7:0.02
    8:0.05
    9:0.04
    10:0.05
    11:0.03
    Negative Logits
     Blink
    -2.02
     Cutter
    -1.96
     Blaster
    -1.94
    Response
    -1.91
     Zero
    -1.85
     Reverse
    -1.83
     Flare
    -1.79
    inis
    -1.77
    pty
    -1.73
     Provided
    -1.72
    POSITIVE LOGITS
    country
    2.61
     countryside
    2.55
     locality
    2.45
    gage
    2.35
     country
    2.33
    town
    2.32
     Philippines
    2.24
    city
    2.19
    STATE
    2.19
    region
    2.17
    Activations Density 0.031%

    No Known Activations