© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 16580
    Prev
    Next
    INDEX
    Explanations

    terms related to processes or guidelines in a technical or formal context

    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
    0:0.03
    1:0.06
    2:0.48
    3:0.04
    4:0.03
    5:0.03
    6:0.03
    7:0.09
    8:0.04
    9:0.04
    10:0.04
    11:0.03
    Negative Logits
    龍
    -3.44
     fifty
    -3.35
     eighty
    -3.30
     nineteen
    -3.28
     sixty
    -3.25
     forty
    -3.15
     seventy
    -3.10
     thirty
    -3.06
     seventeen
    -3.04
     sevent
    -2.94
    POSITIVE LOGITS
     2
    7.74
     3
    6.73
    2
    5.72
     4
    5.32
    3
    4.94
     1
    4.90
    4
    3.74
     5
    3.69
     6
    3.49
     II
    3.03
    Activations Density 0.270%

    No Known Activations