© 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. 5-ATT-KK
    11. 43292
    Prev
    Next
    INDEX
    Explanations

    references to traditional or regional dishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.02
    1:0.02
    2:0.04
    3:0.05
    4:0.02
    5:0.06
    6:0.01
    7:0.03
    8:0.02
    9:0.10
    10:0.42
    11:0.15
    Negative Logits
     firewall
    -1.43
     extradition
    -1.32
     subpoena
    -1.32
    FBI
    -1.30
     FBI
    -1.29
     Galile
    -1.29
    VPN
    -1.28
     SDL
    -1.24
     SWAT
    -1.22
    Investigators
    -1.21
    POSITIVE LOGITS
    isine
    1.85
     edible
    1.75
     Ingredients
    1.74
    Ingredients
    1.72
     servings
    1.65
     tast
    1.65
     ingredients
    1.64
     meal
    1.61
     flavored
    1.60
     tasted
    1.59
    Activations Density 1.005%

    No Known Activations