© 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. 24262
    Prev
    Next
    INDEX
    Explanations

    punctuation marks used to express reactions or actions in writing

    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
    2:0.08
    3:0.04
    4:0.04
    5:0.03
    6:0.23
    7:0.04
    8:0.05
    9:0.29
    10:0.02
    11:0.03
    Negative Logits
     Ott
    -4.24
     Ogre
    -4.07
    hook
    -3.82
     Atkins
    -3.78
     Hatt
    -3.54
    fed
    -3.54
     Mai
    -3.41
     Rapt
    -3.40
    ="#
    -3.36
     ensl
    -3.35
    POSITIVE LOGITS
     Ver
    8.67
    Ver
    8.13
     VER
    6.85
    ver
    6.28
    VER
    5.84
     ver
    5.82
     Veronica
    5.00
     Vernon
    4.75
     verification
    4.59
     Vir
    4.50
    Activations Density 0.011%

    No Known Activations