© 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. 21651
    Prev
    Next
    INDEX
    Explanations

    discussions surrounding the legalization and regulation of marijuana

    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
    0:0.39
    1:0.01
    2:0.18
    3:0.08
    4:0.02
    5:0.08
    6:0.02
    7:0.06
    8:0.06
    9:0.01
    10:0.02
    11:0.01
    Negative Logits
     Titanic
    -3.11
     Eag
    -2.47
     Ao
    -2.44
     Katrina
    -2.41
     Thib
    -2.41
     Hebdo
    -2.34
     Athe
    -2.31
     Stern
    -2.29
     pengu
    -2.26
    ebus
    -2.23
    POSITIVE LOGITS
    arijuana
    3.84
     cultivation
    3.69
     growers
    3.68
     dispensaries
    3.66
     weed
    3.61
     Cannabis
    3.58
     legalization
    3.48
     dispensary
    3.47
     THC
    3.46
     cannabis
    3.40
    Activations Density 0.128%

    No Known Activations