© 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. 17505
    Prev
    Next
    INDEX
    Explanations

    punctuations and common connecting words that signal transitions or emphasis in sentences

    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
    0:0.06
    1:0.06
    2:0.04
    3:0.06
    4:0.06
    5:0.04
    6:0.27
    7:0.04
    8:0.04
    9:0.17
    10:0.04
    11:0.05
    Negative Logits
     Emer
    -3.71
    Clark
    -3.56
     Gil
    -3.56
     Moore
    -3.53
     Clark
    -3.53
     Jacobs
    -3.48
     Levy
    -3.47
     Wol
    -3.41
    Moore
    -3.36
     Wells
    -3.35
    POSITIVE LOGITS
     Brut
    4.32
     nost
    4.03
     Shank
    3.81
     sod
    3.61
     Mast
    3.54
     Punk
    3.44
    Brend
    3.38
     corpor
    3.30
     malt
    3.19
     Sod
    3.18
    Activations Density 0.010%

    No Known Activations