© 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. 13679
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and emotional reflections

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.17
    1:0.03
    2:0.14
    3:0.08
    4:0.07
    5:0.04
    6:0.04
    7:0.26
    8:0.02
    9:0.02
    10:0.05
    11:0.02
    Negative Logits
     Tripoli
    -2.66
     Rhodes
    -2.44
     SAM
    -2.28
     Ulster
    -2.07
     Libyan
    -2.04
     Essex
    -1.99
     Worm
    -1.98
     Rosen
    -1.98
     Bridgewater
    -1.97
     Samp
    -1.95
    POSITIVE LOGITS
    �
    4.29
     �
    3.12
    ️
    2.90
    �
    2.79
    ‎
    2.61
     Blizz
    2.41
     Elsa
    2.40
    �
    2.38
    アル
    2.35
     Ples
    2.31
    Activations Density 6.649%

    No Known Activations