© 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. 21909
    Prev
    Next
    INDEX
    Explanations

    questions and references to reading comprehension issues

    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
    1:0.07
    2:0.06
    3:0.04
    4:0.02
    5:0.03
    6:0.11
    7:0.09
    8:0.01
    9:0.03
    10:0.31
    11:0.04
    Negative Logits
     Stellar
    -3.30
     Bud
    -3.12
     Cluster
    -3.10
     BIT
    -3.04
    uras
    -2.95
    stasy
    -2.94
     Lum
    -2.85
     rays
    -2.85
    irit
    -2.77
     Castro
    -2.77
    POSITIVE LOGITS
     Je
    10.25
    Je
    10.21
    je
    7.04
     je
    6.61
     Jeep
    4.86
     Jae
    4.53
     Wr
    4.38
    jen
    4.21
     Chero
    3.61
     Se
    3.56
    Activations Density 0.004%

    No Known Activations