© 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. 9-ATT-KK
    6. 21164
    Prev
    Next
    INDEX
    Explanations

    terms related to the chemical composition and effects of cannabis

    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
    0:0.12
    1:0.02
    2:0.19
    3:0.11
    4:0.03
    5:0.10
    6:0.03
    7:0.06
    8:0.19
    9:0.03
    10:0.05
    11:0.02
    Negative Logits
    ł
    -3.17
    �
    -3.10
     Lithuan
    -2.76
     Rwanda
    -2.73
     Scand
    -2.70
     resil
    -2.64
    nets
    -2.63
     Balt
    -2.61
     Loch
    -2.59
    debian
    -2.55
    POSITIVE LOGITS
     THC
    4.22
     cannabinoid
    3.70
     cannabinoids
    3.58
    annabin
    3.46
     intox
    2.91
     cannabin
    2.77
     Cannabis
    2.63
     buds
    2.50
     Marijuana
    2.44
     CB
    2.40
    Activations Density 0.004%

    No Known Activations