© 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. 4329
    Prev
    Next
    INDEX
    Explanations

    frequent markers of dialogue or quotations

    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
    3:0.04
    4:0.07
    5:0.05
    6:0.19
    7:0.06
    8:0.11
    9:0.20
    10:0.02
    11:0.05
    Negative Logits
     subsequ
    -3.56
    ega
    -3.37
     sund
    -3.34
    vernment
    -3.33
    Ga
    -3.30
     Alb
    -3.30
    thumbnails
    -3.26
    lyak
    -3.23
    00200000
    -3.23
     Satoshi
    -3.22
    POSITIVE LOGITS
     Piper
    8.96
     Fitzpatrick
    7.49
     Fitz
    5.56
     Fitzgerald
    5.03
     Kier
    4.95
     Dawson
    4.91
     Dickinson
    4.82
     Ember
    4.62
    iper
    4.49
     Gibbs
    4.41
    Activations Density 0.001%

    No Known Activations