© 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. 6518
    Prev
    Next
    INDEX
    Explanations

    sentences expressing perspectives or opinions about actions and responsibilities

    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
    0:0.02
    1:0.02
    2:0.03
    3:0.04
    4:0.06
    5:0.17
    6:0.02
    7:0.03
    8:0.02
    9:0.44
    10:0.02
    11:0.08
    Negative Logits
     waning
    -2.09
     disperse
    -2.05
     dispers
    -2.03
     retreat
    -2.00
     weakening
    -1.99
     clos
    -1.98
     lingering
    -1.97
    flight
    -1.97
    reen
    -1.93
     weaker
    -1.92
    POSITIVE LOGITS
    mean
    2.65
    about
    2.55
    About
    2.49
     Mean
    2.41
     ABOUT
    2.38
     About
    2.28
     about
    2.27
    ictionary
    2.21
     mean
    2.17
     consists
    2.14
    Activations Density 0.173%

    No Known Activations