© 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. 5-ATT-KK
    11. 1751
    Prev
    Next
    INDEX
    Explanations

    references to programming and technical terminology regarding errors and exceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    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
    1:0.24
    2:0.04
    3:0.04
    4:0.03
    5:0.12
    6:0.10
    7:0.05
    8:0.08
    9:0.04
    10:0.07
    11:0.04
    Negative Logits
    686
    -1.73
     Charlotte
    -1.71
     mars
    -1.67
    olit
    -1.66
    870
    -1.63
    CAN
    -1.59
    NRS
    -1.56
    /"
    -1.55
    Arcade
    -1.54
    880
    -1.54
    POSITIVE LOGITS
     Kurd
    2.04
    KEY
    1.86
    yip
    1.84
     guiActive
    1.84
     Dir
    1.80
    key
    1.76
    VERTISEMENT
    1.75
     Slav
    1.74
    ickr
    1.72
     Gujar
    1.64
    Activations Density 0.002%

    No Known Activations