© 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. 30200
    Prev
    Next
    INDEX
    Explanations

    language that expresses opinions, emotions, or subjective experiences

    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
    0:0.02
    1:0.02
    2:0.08
    3:0.13
    4:0.29
    5:0.02
    6:0.10
    7:0.11
    8:0.04
    9:0.04
    10:0.03
    11:0.06
    Negative Logits
    llah
    -1.50
     guiActiveUn
    -1.40
    Kal
    -1.35
    �士
    -1.35
    tesy
    -1.34
    =-=-=-=-
    -1.31
    course
    -1.30
    ipel
    -1.27
     delinqu
    -1.25
    Options
    -1.20
    POSITIVE LOGITS
     fared
    1.42
     pronounce
    1.32
     interpret
    1.31
     intersect
    1.31
    itect
    1.28
    ocating
    1.27
     reformed
    1.27
     Pats
    1.23
     feminists
    1.20
    croft
    1.19
    Activations Density 0.088%

    No Known Activations