© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 21588
    Prev
    Next
    INDEX
    Explanations

    topics related to economic and social conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    1:0.01
    2:0.26
    3:0.15
    4:0.17
    5:0.03
    6:0.05
    7:0.04
    8:0.03
    9:0.03
    10:0.09
    11:0.07
    Negative Logits
     cannabin
    -1.53
     thereto
    -1.38
     portion
    -1.34
    Winged
    -1.32
    ']
    -1.31
     compiling
    -1.30
     volcano
    -1.29
     contents
    -1.29
     Hungry
    -1.26
     reader
    -1.26
    POSITIVE LOGITS
    quickShipAvailable
    2.30
    ategory
    1.72
    entimes
    1.66
    abad
    1.62
     Cosponsors
    1.60
    otally
    1.60
    rates
    1.57
    ithub
    1.54
    complex
    1.53
    aza
    1.52
    Activations Density 0.014%

    No Known Activations