© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14754
    Prev
    Next
    INDEX
    Explanations

    discussions about antioxidants and their effects on health

    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
    0:0.20
    1:0.07
    2:0.04
    3:0.08
    4:0.07
    5:0.03
    6:0.05
    7:0.15
    8:0.04
    9:0.04
    10:0.08
    11:0.09
    Negative Logits
     Apache
    -3.01
    76561
    -2.88
     pods
    -2.86
    raints
    -2.75
     polyg
    -2.74
     Predator
    -2.64
     needle
    -2.63
    Proxy
    -2.55
     Oculus
    -2.50
     Unicorn
    -2.47
    POSITIVE LOGITS
     mitochondrial
    4.41
     antioxidant
    4.28
     mitochond
    4.13
    ioxid
    4.10
     glut
    4.06
     oxidative
    3.91
     ROS
    3.87
     antioxidants
    3.85
     antioxid
    3.25
     oxidation
    3.15
    Activations Density 0.007%

    No Known Activations