© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 16543
    Prev
    Next
    INDEX
    Explanations

    comparative statements about television shows, particularly focusing on American versus British series

    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
    1:0.03
    2:0.08
    3:0.06
    4:0.18
    5:0.04
    6:0.04
    7:0.08
    8:0.06
    9:0.04
    10:0.05
    11:0.23
    Negative Logits
     opin
    -2.60
     conson
    -2.43
    avorite
    -2.43
     notation
    -2.38
     spons
    -2.38
     vowel
    -2.35
    ]"
    -2.26
    ritic
    -2.26
     spacing
    -2.25
     chord
    -2.25
    POSITIVE LOGITS
     Lethal
    3.21
     Murder
    3.15
     Deadly
    3.11
     Monsters
    3.06
     Showdown
    3.06
     Deadpool
    2.95
     Disaster
    2.94
     thriller
    2.88
     Silence
    2.85
     Mysteries
    2.82
    Activations Density 0.136%

    No Known Activations