© 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. 9-ATT-KK
    11. 5481
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols used in written communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.08
    1:0.02
    2:0.06
    3:0.04
    4:0.05
    5:0.03
    6:0.24
    7:0.05
    8:0.07
    9:0.25
    10:0.02
    11:0.03
    Negative Logits
     abdom
    -4.07
    DOM
    -3.63
     Varg
    -3.52
    VM
    -3.48
    vag
    -3.48
    strings
    -3.47
     hiber
    -3.46
     scrut
    -3.38
     DOM
    -3.37
     Fem
    -3.33
    POSITIVE LOGITS
     Cohen
    10.88
     Cooke
    7.92
    Co
    5.64
     Cooper
    5.28
     Cohn
    5.20
     Crosby
    5.05
     Cole
    4.76
     Levine
    4.43
     Russo
    4.43
    Cole
    4.26
    Activations Density 0.010%

    No Known Activations