© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 9604
    Prev
    Next
    INDEX
    Explanations

    mentions of numerical data or statistics related to societal issues

    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
    0:0.04
    1:0.04
    2:0.04
    3:0.11
    4:0.03
    5:0.09
    6:0.04
    7:0.03
    8:0.07
    9:0.02
    10:0.08
    11:0.35
    Negative Logits
     
    -4.81
    ``
    -4.77
    !".
    -4.02
    ?".
    -4.00
       
    -3.80
      
    -3.67
    ".[
    -3.67
    --
    -3.57
    ?).
    -3.56
     ``
    -3.55
    POSITIVE LOGITS
     —
    8.06
     ­
    5.66
     »
    4.42
     POLITICO
    3.86
     @
    3.82
    ­
    3.80
     �
    3.78
     �
    3.72
     pic
    3.70
     ―
    3.67
    Activations Density 0.050%

    No Known Activations