© 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. 39590
    Prev
    Next
    INDEX
    Explanations

    instances of the forward slash symbol

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.11
    3:0.05
    4:0.15
    5:0.04
    6:0.12
    7:0.07
    8:0.03
    9:0.06
    10:0.07
    11:0.21
    Negative Logits
    taboola
    -1.94
    inventoryQuantity
    -1.93
    nels
    -1.91
    の魔
    -1.72
    soDeliveryDate
    -1.62
    DragonMagazine
    -1.57
    �
    -1.57
    oir
    -1.52
    ucci
    -1.52
    女
    -1.52
    POSITIVE LOGITS
     Birthday
    1.83
     Hung
    1.60
     Zen
    1.56
    Hung
    1.49
     Mim
    1.49
     pets
    1.49
     stunned
    1.42
     Hungary
    1.38
     Hungarian
    1.35
     Shaman
    1.35
    Activations Density 0.000%

    No Known Activations