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

    Neuronpedia

    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. 9-ATT-KK
    11. 19459
    Prev
    Next
    INDEX
    Explanations

    mentions of media platforms and their impact on news consumption

    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
    0:0.17
    1:0.01
    2:0.33
    3:0.12
    4:0.02
    5:0.10
    6:0.03
    7:0.04
    8:0.05
    9:0.02
    10:0.03
    11:0.03
    Negative Logits
     temperatures
    -2.53
    Condition
    -2.45
     サーティワン
    -2.35
     irrad
    -2.32
    魔
    -2.31
    Armor
    -2.27
    urized
    -2.27
     CRC
    -2.27
     precaution
    -2.26
    aterasu
    -2.25
    POSITIVE LOGITS
     Snapchat
    4.06
     Sharing
    4.00
     Facebook
    3.88
    Twitter
    3.82
     retweet
    3.80
     WhatsApp
    3.78
     Messenger
    3.61
     Twitter
    3.58
     Gmail
    3.56
     LinkedIn
    3.54
    Activations Density 0.882%

    No Known Activations