© 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. 47108
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters, particularly those used to emphasize or separate statements

    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
    0:0.05
    1:0.04
    2:0.07
    3:0.10
    4:0.09
    5:0.04
    6:0.09
    7:0.07
    8:0.09
    9:0.06
    10:0.12
    11:0.11
    Negative Logits
    ufact
    -1.42
     plantations
    -1.31
    bryce
    -1.31
    nery
    -1.28
    okia
    -1.27
     intercepted
    -1.24
     subcontract
    -1.24
     ashore
    -1.23
     cultiv
    -1.18
     msec
    -1.16
    POSITIVE LOGITS
    Check
    1.68
    Please
    1.61
    Comments
    1.60
    Recommended
    1.59
    CHECK
    1.56
    Click
    1.55
    Follow
    1.55
    Review
    1.52
    DON
    1.50
     Please
    1.49
    Activations Density 0.022%

    No Known Activations