© 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. 21651
    Prev
    Next
    INDEX
    Explanations

    proper nouns and significant quantities related to themes of finance and rebates

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.10
    1:0.25
    2:0.04
    3:0.05
    4:0.03
    5:0.15
    6:0.03
    7:0.02
    8:0.16
    9:0.06
    10:0.03
    11:0.03
    Negative Logits
    oat
    -1.87
    rir
    -1.84
    essee
    -1.83
    olas
    -1.81
    lis
    -1.75
    las
    -1.73
    etta
    -1.71
    ua
    -1.71
    lee
    -1.70
    leep
    -1.67
    POSITIVE LOGITS
    ":[{"
    1.85
    udeb
    1.74
    FUL
    1.71
    PsyNetMessage
    1.67
     conclud
    1.63
    },{"
    1.63
    competitive
    1.62
     :-)
    1.61
     reluct
    1.59
    BuyableInstoreAndOnline
    1.56
    Activations Density 0.012%

    No Known Activations