© 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. 10865
    Prev
    Next
    INDEX
    Explanations

    terms related to choice and preference in products and experiences

    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
    1:0.03
    2:0.09
    3:0.17
    4:0.03
    5:0.07
    6:0.03
    7:0.07
    8:0.04
    9:0.03
    10:0.28
    11:0.03
    Negative Logits
     favorites
    -2.92
     pick
    -2.68
     whenever
    -2.67
     cheaper
    -2.59
     whichever
    -2.54
     quicker
    -2.54
     favourites
    -2.43
     onto
    -2.40
     wherever
    -2.38
     favored
    -2.37
    POSITIVE LOGITS
    teness
    2.32
     millenn
    2.07
    cedented
    2.07
    ODUCT
    2.06
    ensable
    2.05
    imeo
    1.99
    REF
    1.97
    lvl
    1.95
    ANI
    1.94
    interrupted
    1.91
    Activations Density 0.001%

    No Known Activations