© 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. 11017
    Prev
    Next
    INDEX
    Explanations

    questions and statements about character motivations and actions within narratives

    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
    0:0.08
    1:0.02
    2:0.06
    3:0.04
    4:0.07
    5:0.03
    6:0.21
    7:0.06
    8:0.06
    9:0.25
    10:0.03
    11:0.05
    Negative Logits
     Esper
    -3.92
    bis
    -3.75
    cham
    -3.68
     bom
    -3.60
    VB
    -3.50
     incorpor
    -3.48
    ratom
    -3.30
    atra
    -3.28
     XIV
    -3.21
    akura
    -3.13
    POSITIVE LOGITS
     Rick
    9.70
    Rick
    9.59
     Morty
    7.62
     Daryl
    4.92
    rick
    4.86
     Mick
    4.81
     Ricky
    4.71
     Sick
    4.23
     Hick
    4.22
    ick
    4.17
    Activations Density 0.010%

    No Known Activations