© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 12607
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions in written text

    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
    0:0.10
    1:0.02
    2:0.06
    3:0.03
    4:0.06
    5:0.04
    6:0.23
    7:0.05
    8:0.10
    9:0.19
    10:0.02
    11:0.05
    Negative Logits
     bracelet
    -4.18
    tie
    -3.92
     php
    -3.81
     Jace
    -3.80
    arte
    -3.67
     brid
    -3.66
    ulture
    -3.65
     Spiral
    -3.63
     tul
    -3.62
    artz
    -3.62
    POSITIVE LOGITS
     McM
    11.63
    Mc
    6.89
     McKay
    6.16
     McGee
    5.77
     McG
    5.38
     McK
    5.26
     Corm
    5.22
     McInt
    5.19
     McKenzie
    5.19
     Mack
    5.16
    Activations Density 0.001%

    No Known Activations