© 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 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. 13536
    Prev
    Next
    INDEX
    Explanations

    instances of quoted speech or attributions in the text

    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
    0:0.06
    1:0.02
    2:0.06
    3:0.04
    4:0.06
    5:0.02
    6:0.27
    7:0.05
    8:0.05
    9:0.26
    10:0.02
    11:0.03
    Negative Logits
     ESC
    -4.57
     pse
    -4.36
     Huma
    -4.30
     grease
    -4.03
    utory
    -3.99
     surrogate
    -3.67
    518
    -3.67
     curry
    -3.62
     contrace
    -3.62
    hao
    -3.61
    POSITIVE LOGITS
     Mart
    11.25
    Mart
    10.85
    mart
    8.07
     mart
    7.84
     Martinez
    6.92
     Marty
    6.73
     Lambert
    4.79
    Mars
    4.71
    Mich
    4.55
     Martin
    4.50
    Activations Density 0.005%

    No Known Activations