© 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. 14364
    Prev
    Next
    INDEX
    Explanations

    phrases related to alcoholic beverages and their consumption

    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
    0:0.17
    1:0.08
    2:0.05
    3:0.05
    4:0.05
    5:0.03
    6:0.08
    7:0.14
    8:0.02
    9:0.03
    10:0.18
    11:0.07
    Negative Logits
    Iterator
    -2.70
    UTF
    -2.69
    ESA
    -2.69
    hler
    -2.66
     Kaplan
    -2.63
    ��
    -2.56
     kinderg
    -2.54
     Hawking
    -2.53
     appl
    -2.52
    ansson
    -2.49
    POSITIVE LOGITS
     rum
    6.09
     Rum
    5.55
    Rum
    4.31
     gin
    4.00
     Jamaica
    3.79
     Jama
    3.73
     Drum
    3.46
    rum
    3.45
     sham
    3.34
     whiskey
    3.30
    Activations Density 0.002%

    No Known Activations