© 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. 10354
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences or opinions regarding the use of kratom for pain management

    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
    1:0.01
    2:0.23
    3:0.06
    4:0.03
    5:0.08
    6:0.05
    7:0.05
    8:0.15
    9:0.05
    10:0.03
    11:0.02
    Negative Logits
     Rockets
    -3.25
     Shap
    -3.11
    asketball
    -3.09
    thodox
    -2.85
     Guardiola
    -2.79
     Collider
    -2.77
     Astros
    -2.74
     Shinra
    -2.69
    stellar
    -2.66
     Transformers
    -2.64
    POSITIVE LOGITS
    ratom
    6.38
     DEA
    4.29
     opium
    3.57
     herbal
    3.50
     alk
    3.45
     opioid
    3.38
     bot
    3.29
     leaf
    3.23
     medicinal
    3.21
     fentanyl
    3.19
    Activations Density 0.005%

    No Known Activations