© 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. 7973
    Prev
    Next
    INDEX
    Explanations

    references to events, gatherings, and audiences involving notable figures and their interactions

    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
    0:0.07
    1:0.02
    2:0.04
    3:0.17
    4:0.03
    5:0.11
    6:0.01
    7:0.05
    8:0.03
    9:0.02
    10:0.35
    11:0.05
    Negative Logits
     Originally
    -2.01
    gone
    -1.97
    brainer
    -1.93
     guess
    -1.85
     Designs
    -1.80
    ealous
    -1.78
    iances
    -1.74
     guesses
    -1.70
     wears
    -1.69
    uristic
    -1.69
    POSITIVE LOGITS
     pilgrims
    2.01
     traged
    1.96
    ─
    1.95
    闘
    1.89
    ridge
    1.88
    racuse
    1.85
     arrivals
    1.82
    �
    1.77
    �
    1.76
    機
    1.72
    Activations Density 0.101%

    No Known Activations