© 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. 21011
    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
    0:0.08
    1:0.08
    2:0.09
    3:0.07
    4:0.09
    5:0.08
    6:0.06
    7:0.07
    8:0.08
    9:0.07
    10:0.09
    11:0.09
    Negative Logits
    =$
    -2.81
    redd
    -2.45
    =""
    -2.41
     demo
    -2.40
    amazon
    -2.38
     dads
    -2.38
    ��
    -2.35
     BELOW
    -2.32
     Shutterstock
    -2.25
     egalitarian
    -2.24
    POSITIVE LOGITS
    pell
    2.85
    amiya
    2.56
    ogun
    2.52
     Franç
    2.49
    nesium
    2.44
     Aircraft
    2.41
    ?)
    2.36
     Indust
    2.34
    augh
    2.33
    ivating
    2.33
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.