© 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. 7596
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to significant changes and their impact across various 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
    0:0.02
    1:0.02
    2:0.03
    3:0.05
    4:0.06
    5:0.22
    6:0.02
    7:0.03
    8:0.02
    9:0.38
    10:0.02
    11:0.06
    Negative Logits
     craw
    -2.35
    stretched
    -2.14
     cher
    -2.13
     empt
    -2.11
    verages
    -2.05
     tatt
    -2.05
    ishly
    -1.99
     Tweet
    -1.99
     openly
    -1.95
     retweet
    -1.93
    POSITIVE LOGITS
     occur
    2.97
    soDeliveryDate
    2.82
     occurred
    2.53
    actionDate
    2.50
     relate
    2.46
     require
    2.40
     Introduced
    2.40
    include
    2.34
     involve
    2.34
    aceutical
    2.27
    Activations Density 0.097%

    No Known Activations