© 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. 5-ATT-KK
    11. 7599
    Prev
    Next
    INDEX
    Explanations

    words associated with food adulteration or contamination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.03
    2:0.06
    3:0.04
    4:0.05
    5:0.04
    6:0.09
    7:0.19
    8:0.05
    9:0.06
    10:0.24
    11:0.06
    Negative Logits
     mentors
    -1.85
     Apostles
    -1.71
     Lessons
    -1.71
     applauded
    -1.69
     lightning
    -1.67
     pillars
    -1.66
     Transform
    -1.64
     magnification
    -1.63
     discipl
    -1.61
     laughter
    -1.58
    POSITIVE LOGITS
     adul
    2.07
    upid
    1.83
    icides
    1.83
    ipop
    1.81
    achus
    1.80
    puter
    1.77
    plet
    1.77
     offending
    1.75
    avorite
    1.74
    ixture
    1.73
    Activations Density 0.000%

    No Known Activations