© 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. 44652
    Prev
    Next
    INDEX
    Explanations

    mentions of groups or pairs of individuals or entities

    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
    0:0.01
    1:0.01
    2:0.04
    3:0.03
    4:0.02
    5:0.08
    6:0.02
    7:0.02
    8:0.08
    9:0.06
    10:0.50
    11:0.06
    Negative Logits
    markets
    -1.92
    artifacts
    -1.92
    omed
    -1.84
     prest
    -1.83
    gradient
    -1.77
    market
    -1.75
    grain
    -1.68
     wholesale
    -1.68
     shortages
    -1.67
     ration
    -1.67
    POSITIVE LOGITS
     duo
    2.34
     brothers
    2.26
     twins
    2.21
    Together
    1.92
     siblings
    1.87
     Joined
    1.87
     separately
    1.84
     respectively
    1.81
     sisters
    1.81
     Bastard
    1.81
    Activations Density 0.627%

    No Known Activations