© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 19512
    Prev
    Next
    INDEX
    Explanations

    references to software downloads and updates

    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
    0:0.12
    1:0.03
    2:0.05
    3:0.06
    4:0.08
    5:0.04
    6:0.07
    7:0.26
    8:0.02
    9:0.07
    10:0.04
    11:0.09
    Negative Logits
     inherited
    -1.98
     Parsons
    -1.88
     photographed
    -1.88
    eele
    -1.83
     recruits
    -1.80
     drafting
    -1.78
     Boeing
    -1.78
     Pryor
    -1.77
     prototyp
    -1.77
    ahime
    -1.76
    POSITIVE LOGITS
     Torrent
    2.46
    yip
    2.36
     Xperia
    2.29
     torrent
    2.24
    rar
    2.09
     Lite
    2.08
     zip
    2.04
    Crypt
    2.04
     mp
    2.01
     Zion
    2.00
    Activations Density 0.048%

    No Known Activations