© 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. 16941
    Prev
    Next
    INDEX
    Explanations

    brand names and proper nouns associated with organizations or products

    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
    0:0.05
    1:0.19
    2:0.02
    3:0.02
    4:0.02
    5:0.47
    6:0.02
    7:0.01
    8:0.05
    9:0.05
    10:0.03
    11:0.02
    Negative Logits
     kg
    -1.78
     innocence
    -1.76
     Pes
    -1.73
     microw
    -1.71
     Kir
    -1.70
     ir
    -1.68
     adam
    -1.68
     psi
    -1.66
     LAT
    -1.65
     NIC
    -1.64
    POSITIVE LOGITS
    pop
    3.02
    organ
    2.95
    scan
    2.92
    mop
    2.92
    split
    2.89
    forum
    2.87
    grad
    2.82
    floor
    2.80
    quiet
    2.79
    business
    2.77
    Activations Density 0.229%

    No Known Activations