© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 20940
    Prev
    Next
    INDEX
    Explanations

    elements related to future content updates or developments

    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
    0:0.15
    1:0.10
    2:0.07
    3:0.07
    4:0.06
    5:0.02
    6:0.13
    7:0.09
    8:0.03
    9:0.04
    10:0.09
    11:0.09
    Negative Logits
     Malcolm
    -3.15
    milo
    -3.06
     Cox
    -3.03
     Chattanooga
    -3.02
     Berger
    -3.01
     Canaver
    -3.01
     Chip
    -2.97
     Chomsky
    -2.88
    abet
    -2.85
    colm
    -2.78
    POSITIVE LOGITS
     Realm
    7.10
     Realms
    5.84
     realms
    5.56
     realm
    5.34
     dungeons
    3.80
     dungeon
    3.56
     kingdom
    3.44
     castles
    3.38
     Kingdom
    3.28
     Strongh
    3.26
    Activations Density 0.002%

    No Known Activations