© 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. 9-ATT-KK
    11. 24422
    Prev
    Next
    INDEX
    Explanations

    references to alcoholic beverages and their qualities

    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
    0:0.42
    1:0.01
    2:0.11
    3:0.10
    4:0.03
    5:0.07
    6:0.04
    7:0.04
    8:0.06
    9:0.03
    10:0.02
    11:0.02
    Negative Logits
     Canaver
    -2.94
     gymn
    -2.90
     Proced
    -2.71
     modem
    -2.68
     Gamergate
    -2.62
    ospace
    -2.42
    software
    -2.34
     procedural
    -2.33
     Motorola
    -2.33
     router
    -2.32
    POSITIVE LOGITS
     brewed
    6.02
     ABV
    5.44
     drinkers
    5.41
     brew
    5.34
     tasting
    5.20
     brewery
    5.02
     bottles
    4.98
     brewers
    4.97
    Bott
    4.93
     brewer
    4.91
    Activations Density 0.833%

    No Known Activations