© 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. 9793
    Prev
    Next
    INDEX
    Explanations

    references to AMC television series and their seasons

    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
    0:0.27
    1:0.02
    2:0.07
    3:0.06
    4:0.04
    5:0.09
    6:0.05
    7:0.05
    8:0.19
    9:0.05
    10:0.04
    11:0.03
    Negative Logits
     Poké
    -3.54
     Surf
    -3.12
     Cele
    -3.03
    Poké
    -2.95
     melody
    -2.94
     Jelly
    -2.92
    ğ
    -2.90
     Fishing
    -2.89
     Poke
    -2.87
    Magikarp
    -2.85
    POSITIVE LOGITS
     AMC
    5.95
     Hannibal
    3.20
     vampires
    3.09
    heimer
    3.05
     Romero
    3.02
     Boone
    2.93
     Jesse
    2.92
     Chattanooga
    2.85
    ouri
    2.76
     dealership
    2.72
    Activations Density 0.002%

    No Known Activations