© 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. 38319
    Prev
    Next
    INDEX
    Explanations

    references to important artifacts or figures in history

    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
    0:0.15
    1:0.37
    2:0.03
    3:0.02
    4:0.02
    5:0.20
    6:0.02
    7:0.01
    8:0.04
    9:0.03
    10:0.03
    11:0.02
    Negative Logits
    angel
    -2.75
    amera
    -2.55
    ache
    -2.52
    enei
    -2.51
    ale
    -2.51
    gae
    -2.48
    apache
    -2.46
    union
    -2.45
    index
    -2.41
    enth
    -2.39
    POSITIVE LOGITS
     M
    3.27
     E
    3.17
     C
    3.15
     N
    3.01
     R
    2.93
     Q
    2.87
     L
    2.85
     S
    2.77
     D
    2.68
     G
    2.68
    Activations Density 0.091%

    No Known Activations