© 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. 10-ATT-KK
    11. 17149
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitions between phrases that suggest continuation or addition of ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.06
    2:0.10
    3:0.08
    4:0.07
    5:0.05
    6:0.07
    7:0.18
    8:0.04
    9:0.07
    10:0.04
    11:0.11
    Negative Logits
     Download
    -6.72
     download
    -6.57
     downloading
    -6.31
     downloaded
    -6.25
     downloads
    -6.03
    Download
    -5.94
    download
    -5.76
     Downloads
    -5.61
     downloadable
    -5.11
    Torrent
    -4.04
    POSITIVE LOGITS
     Nichols
    3.19
    mouth
    3.13
     Spirits
    2.96
     Cah
    2.93
     Scalia
    2.87
     spirits
    2.84
     Christy
    2.84
     Ish
    2.82
     Corinth
    2.81
     Greenberg
    2.79
    Activations Density 0.000%

    No Known Activations