© 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. 9826
    Prev
    Next
    INDEX
    Explanations

    references to various roles and relationships in personal and social contexts

    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
    1:0.01
    2:0.03
    3:0.03
    4:0.07
    5:0.17
    6:0.02
    7:0.04
    8:0.01
    9:0.45
    10:0.01
    11:0.06
    Negative Logits
     closures
    -2.73
    ibraries
    -2.61
    aways
    -2.32
     resolutions
    -2.31
    items
    -2.30
    Changes
    -2.30
    urches
    -2.29
    icals
    -2.28
    tails
    -2.27
    azines
    -2.24
    POSITIVE LOGITS
     himself
    4.90
     whom
    4.79
    who
    4.38
     who
    4.36
     his
    4.30
    His
    4.29
    his
    4.26
     His
    4.19
     Himself
    4.05
     whose
    3.88
    Activations Density 1.435%

    No Known Activations