© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 44062
    Prev
    Next
    INDEX
    Explanations

    references to media, stories, and communication

    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
    0:0.11
    1:0.38
    2:0.02
    3:0.02
    4:0.03
    5:0.16
    6:0.02
    7:0.02
    8:0.07
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
     Cad
    -1.98
     Berk
    -1.89
     Myr
    -1.88
     Cloak
    -1.83
     Ballard
    -1.79
    Clark
    -1.78
    orb
    -1.77
     Beacon
    -1.77
     Chau
    -1.76
    erion
    -1.74
    POSITIVE LOGITS
    soDeliveryDate
    2.26
     ABOUT
    2.02
     about
    2.01
     insulting
    2.01
     bout
    1.97
    icts
    1.85
     detailing
    1.77
     wrench
    1.77
    nces
    1.74
     sidx
    1.74
    Activations Density 0.013%

    No Known Activations