© 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. 12662
    Prev
    Next
    INDEX
    Explanations

    references to dates and numerical data

    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
    0:0.03
    1:0.06
    2:0.02
    3:0.05
    4:0.04
    5:0.05
    6:0.06
    7:0.03
    8:0.03
    9:0.50
    10:0.04
    11:0.04
    Negative Logits
    Roberts
    -3.65
     Giov
    -3.58
     Robertson
    -3.51
    ORE
    -3.48
    ore
    -3.44
    oro
    -3.38
    ":"/
    -3.37
     Bore
    -3.37
     Hills
    -3.35
    ill
    -3.26
    POSITIVE LOGITS
    January
    5.77
     January
    5.37
     Jan
    4.73
    Jan
    4.72
     jan
    4.33
    ien
    3.94
    jan
    3.50
    ISTER
    3.46
     ABE
    3.35
     Schumer
    3.31
    Activations Density 0.018%

    No Known Activations