© 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. 43958
    Prev
    Next
    INDEX
    Explanations

    phrases related to dominance or authority in competitive contexts

    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
    2:0.06
    3:0.06
    4:0.20
    5:0.02
    6:0.10
    7:0.31
    8:0.03
    9:0.03
    10:0.04
    11:0.05
    Negative Logits
    Serv
    -1.93
    rification
    -1.93
     ($)
    -1.86
    +(
    -1.84
     (%)
    -1.81
    ILLE
    -1.75
     actionGroup
    -1.65
    imei
    -1.63
     Harm
    -1.60
    contained
    -1.59
    POSITIVE LOGITS
     benches
    1.95
     necks
    1.89
     bandwagon
    1.89
     heels
    1.87
     curls
    1.75
     corners
    1.75
     chairs
    1.74
     tails
    1.73
     hamm
    1.70
     shores
    1.69
    Activations Density 0.001%

    No Known Activations