© 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. 10730
    Prev
    Next
    INDEX
    Explanations

    phrases that express the complexity or nuances of a situation

    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
    0:0.03
    1:0.04
    2:0.02
    3:0.03
    4:0.04
    5:0.11
    6:0.03
    7:0.05
    8:0.03
    9:0.50
    10:0.02
    11:0.05
    Negative Logits
     lasting
    -2.49
     worn
    -2.35
     usable
    -2.33
     trough
    -2.28
     ridden
    -2.28
     effected
    -2.18
     benefiting
    -2.09
     undertaken
    -2.07
     happening
    -2.06
     entering
    -2.05
    POSITIVE LOGITS
    ially
    2.43
    OST
    2.25
    Orig
    2.24
    onse
    2.24
    apolog
    2.12
    itatively
    2.06
    icip
    2.00
    ifully
    1.98
    uate
    1.97
    handedly
    1.95
    Activations Density 0.120%

    No Known Activations