© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 3232
    Prev
    Next
    INDEX
    Explanations

    terms related to alcohol consumption and its consequences

    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
    0:0.18
    1:0.02
    2:0.27
    3:0.09
    4:0.03
    5:0.11
    6:0.06
    7:0.05
    8:0.04
    9:0.04
    10:0.03
    11:0.03
    Negative Logits
     Pwr
    -3.27
     Canaver
    -3.15
    ilater
    -2.83
     Siem
    -2.70
     pivot
    -2.67
     UID
    -2.67
     Ai
    -2.64
     Motorola
    -2.58
     Mesh
    -2.54
     Architect
    -2.50
    POSITIVE LOGITS
     alcohol
    5.82
    cohol
    5.78
    alcohol
    5.69
     intoxication
    5.69
     alcoholic
    5.54
     drinking
    5.46
     drank
    5.39
     drinkers
    5.35
     drink
    5.33
     booze
    5.32
    Activations Density 0.166%

    No Known Activations