© 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. 21740
    Prev
    Next
    INDEX
    Explanations

    references to historical events or periods

    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
    0:0.02
    1:0.02
    2:0.05
    3:0.06
    4:0.14
    5:0.02
    6:0.11
    7:0.28
    8:0.03
    9:0.04
    10:0.07
    11:0.11
    Negative Logits
    ledged
    -1.43
    azar
    -1.40
    覚醒
    -1.37
    ilitary
    -1.36
    ctor
    -1.33
    AIN
    -1.30
    AAAA
    -1.30
    haps
    -1.29
    ographically
    -1.28
    forces
    -1.27
    POSITIVE LOGITS
     downtime
    1.69
    downs
    1.53
     buildup
    1.50
     renovations
    1.46
     visits
    1.45
     visit
    1.35
     checkout
    1.35
     Peel
    1.33
     festivities
    1.32
     Exhibition
    1.31
    Activations Density 0.067%

    No Known Activations