© 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. 10-ATT-KK
    11. 21028
    Prev
    Next
    INDEX
    Explanations

    elements related to chemistry and compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.11
    1:0.12
    2:0.04
    3:0.03
    4:0.03
    5:0.02
    6:0.06
    7:0.07
    8:0.02
    9:0.03
    10:0.38
    11:0.04
    Negative Logits
    leon
    -3.22
    wen
    -3.14
     Le
    -2.91
    Leon
    -2.90
    子
    -2.87
     AF
    -2.85
     Ames
    -2.84
    eger
    -2.82
     Bett
    -2.77
     Berks
    -2.73
    POSITIVE LOGITS
     Cr
    10.51
    Cr
    9.60
     cr
    8.47
    cr
    7.97
     CR
    5.36
     Crane
    5.10
    CR
    4.93
     crater
    4.64
     Fr
    4.54
     crabs
    4.54
    Activations Density 0.031%

    No Known Activations