© 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. 20371
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and user experience, particularly in software and online services

    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
    1:0.02
    2:0.04
    3:0.05
    4:0.07
    5:0.46
    6:0.02
    7:0.04
    8:0.01
    9:0.16
    10:0.01
    11:0.05
    Negative Logits
     unsur
    -3.18
     reasonably
    -3.13
     notwithstanding
    -3.02
    rather
    -2.97
     doubtless
    -2.95
    oubted
    -2.93
     nodded
    -2.82
     hail
    -2.81
     concluded
    -2.79
     duly
    -2.72
    POSITIVE LOGITS
     anymore
    5.54
     manually
    3.82
     again
    3.78
    again
    3.28
     every
    3.26
    Every
    3.05
     everyday
    2.98
     yourself
    2.98
     constantly
    2.95
     Again
    2.92
    Activations Density 0.341%

    No Known Activations