© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 8489
    Prev
    Next
    INDEX
    Explanations

    references to legal and regulatory matters related to businesses

    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
    0:0.24
    1:0.03
    2:0.04
    3:0.07
    4:0.05
    5:0.01
    6:0.11
    7:0.16
    8:0.01
    9:0.04
    10:0.09
    11:0.08
    Negative Logits
     Desmond
    -3.61
     Hollande
    -3.53
     Titanic
    -3.26
     Senegal
    -3.26
     Maurit
    -3.25
     Ghana
    -2.87
     Dirk
    -2.85
     pengu
    -2.83
     Cheney
    -2.82
     Africans
    -2.82
    POSITIVE LOGITS
     dispensary
    7.12
     dispensaries
    6.67
     Cannabis
    4.37
     storefront
    4.11
     Disp
    4.07
    arijuana
    3.88
     cannabis
    3.82
     THC
    3.64
     cannabinoid
    3.63
     pharmacies
    3.59
    Activations Density 0.018%

    No Known Activations