© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 15099
    Prev
    Next
    INDEX
    Explanations

    references to character interactions and relationships in a narrative context

    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
    0:0.29
    1:0.06
    2:0.06
    3:0.08
    4:0.07
    5:0.03
    6:0.06
    7:0.10
    8:0.02
    9:0.04
    10:0.09
    11:0.05
    Negative Logits
     Brune
    -3.92
    Saudi
    -3.83
     Saudis
    -3.76
     Saudi
    -3.63
     Dolphin
    -3.60
     FISA
    -3.59
     reefs
    -3.58
     Mariners
    -3.55
     Riyadh
    -3.50
     fisheries
    -3.47
    POSITIVE LOGITS
     AMC
    6.55
     zombies
    5.90
     zombie
    5.88
     Walking
    5.40
     Zombie
    5.28
     Zombies
    5.27
     Daryl
    5.21
     Romero
    4.73
     undead
    4.71
     Rick
    3.95
    Activations Density 0.014%

    No Known Activations