© 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. 30242
    Prev
    Next
    INDEX
    Explanations

    symbols and references related to online communication and social media

    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
    0:0.16
    1:0.28
    2:0.04
    3:0.03
    4:0.04
    5:0.11
    6:0.02
    7:0.05
    8:0.04
    9:0.06
    10:0.04
    11:0.06
    Negative Logits
    ゼウス
    -2.37
    iband
    -2.21
    uggle
    -2.06
    asar
    -1.96
    remlin
    -1.91
    annis
    -1.86
    illary
    -1.85
    scill
    -1.84
    ioxide
    -1.81
    ilial
    -1.80
    POSITIVE LOGITS
     @
    2.93
    @
    2.30
     "@
    2.28
     <@
    2.24
     ±
    2.09
     [+
    1.76
    /+
    1.76
     /
    1.73
     Photography
    1.73
    \/\/
    1.72
    Activations Density 0.004%

    No Known Activations