© 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. 19612
    Prev
    Next
    INDEX
    Explanations

    references to specific titles and sequences within a structured content 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
    0:0.14
    1:0.04
    2:0.05
    3:0.05
    4:0.06
    5:0.03
    6:0.07
    7:0.31
    8:0.03
    9:0.04
    10:0.06
    11:0.07
    Negative Logits
     Vive
    -2.72
     �
    -2.52
    �
    -2.49
     rune
    -2.44
     Cthulhu
    -2.38
    Thor
    -2.37
    Web
    -2.37
    ._
    -2.35
    Rub
    -2.34
     Sieg
    -2.33
    POSITIVE LOGITS
     Joan
    2.46
    aucus
    2.44
    phia
    2.40
    mor
    2.38
    haps
    2.28
    levard
    2.24
    CHO
    2.23
     Jordanian
    2.23
     Jericho
    2.22
    colm
    2.21
    Activations Density 0.002%

    No Known Activations