© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43714
    Prev
    Next
    INDEX
    Explanations

    references to reading or content recommendations

    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
    0:0.02
    1:0.03
    2:0.04
    3:0.09
    4:0.08
    5:0.04
    6:0.20
    7:0.04
    8:0.03
    9:0.06
    10:0.08
    11:0.25
    Negative Logits
     grains
    -1.91
     scrolls
    -1.84
     Journals
    -1.80
     oats
    -1.79
     corros
    -1.78
     mathemat
    -1.62
     biotech
    -1.59
    Condition
    -1.56
     looting
    -1.53
     cereal
    -1.53
    POSITIVE LOGITS
     Blanc
    1.62
     Deer
    1.62
    vae
    1.57
     Pole
    1.57
     Luna
    1.56
     Osaka
    1.54
     Torres
    1.54
    ğ
    1.52
     Yoshi
    1.50
    ois
    1.50
    Activations Density 0.002%

    No Known Activations