© 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. 22967
    Prev
    Next
    INDEX
    Explanations

    references to significant cultural or societal events and achievements

    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
    0:0.07
    1:0.13
    2:0.07
    3:0.06
    4:0.02
    5:0.02
    6:0.25
    7:0.09
    8:0.01
    9:0.04
    10:0.09
    11:0.08
    Negative Logits
     nib
    -3.09
    markets
    -3.01
     unpop
    -2.82
    arak
    -2.68
     upstream
    -2.67
     Ack
    -2.64
    iat
    -2.45
     ANG
    -2.44
     Nib
    -2.44
    iatus
    -2.42
    POSITIVE LOGITS
    Hall
    8.57
     Hall
    8.37
     hall
    6.08
     Halls
    6.02
     halls
    5.24
    hall
    5.11
     hallway
    3.77
     Rooms
    3.69
    Hill
    3.49
     Stadium
    3.39
    Activations Density 0.019%

    No Known Activations