© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 2613
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    0:0.09
    1:0.09
    2:0.08
    3:0.08
    4:0.09
    5:0.07
    6:0.06
    7:0.08
    8:0.07
    9:0.08
    10:0.07
    11:0.08
    Negative Logits
    pmwiki
    -3.76
    psc
    -3.65
    selage
    -3.21
    Ton
    -2.99
    uko
    -2.90
    portion
    -2.83
    atown
    -2.77
    sie
    -2.72
     reluct
    -2.70
    Wheel
    -2.67
    POSITIVE LOGITS
     Austrian
    3.29
     MSM
    3.01
     Patri
    2.99
     Cardinals
    2.96
     Israeli
    2.89
     Sheikh
    2.89
     Ukip
    2.85
     Rab
    2.83
     Registrar
    2.82
     Patriarch
    2.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.