Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 20704
    Prev
    Next
    INDEX
    Explanations

    references to the game's development and community involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.18
    1:0.03
    2:0.11
    3:0.07
    4:0.05
    5:0.06
    6:0.06
    7:0.05
    8:0.23
    9:0.04
    10:0.02
    11:0.05
    Negative Logits
     Juda
    -3.10
    uku
    -2.97
     Nadu
    -2.97
    govtrack
    -2.96
     Okin
    -2.92
    awaru
    -2.88
     Zimbabwe
    -2.87
    vim
    -2.86
     Hiroshima
    -2.85
    Wisconsin
    -2.81
    POSITIVE LOGITS
     Squadron
    5.15
     Citizen
    4.01
     hangar
    4.00
     droid
    3.96
     CCP
    3.92
     EVE
    3.88
     Roberts
    3.67
     cockpit
    3.66
     Drone
    3.63
     Star
    3.63
    Activations Density 0.003%

    No Known Activations