© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 23522
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and sentence structures

    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
    1:0.03
    2:0.04
    3:0.05
    4:0.04
    5:0.03
    6:0.20
    7:0.05
    8:0.07
    9:0.29
    10:0.03
    11:0.04
    Negative Logits
     PKK
    -4.03
     tul
    -3.81
    �
    -3.75
    flag
    -3.65
    KA
    -3.59
     Chains
    -3.57
     Gul
    -3.56
    Turkish
    -3.53
    vag
    -3.51
    Gab
    -3.51
    POSITIVE LOGITS
     Neal
    10.88
    Neal
    10.21
     Rox
    4.31
     Morrison
    4.29
     Meier
    4.26
     Norris
    4.23
     Thornton
    4.17
     Payne
    4.13
     Hew
    4.04
     Nets
    4.03
    Activations Density 0.001%

    No Known Activations