© 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. 9-ATT-KK
    11. 8372
    Prev
    Next
    INDEX
    Explanations

    references to legal concerns and societal issues related to drugs and their impact on communities

    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
    0:0.04
    1:0.08
    2:0.04
    3:0.07
    4:0.03
    5:0.05
    6:0.10
    7:0.04
    8:0.04
    9:0.36
    10:0.04
    11:0.07
    Negative Logits
     Lem
    -3.37
     Des
    -3.27
     Scher
    -3.10
     MU
    -3.06
     Michel
    -2.85
     Cutter
    -2.81
    iere
    -2.80
    eer
    -2.78
     Scourge
    -2.77
     Sai
    -2.76
    POSITIVE LOGITS
    �
    5.89
    �
    3.64
    Bal
    3.62
    dal
    3.60
    ナ
    3.58
     Baird
    3.56
    bal
    3.46
     Cosponsors
    3.35
    き
    3.32
    gal
    3.27
    Activations Density 0.439%

    No Known Activations