© 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. 19416
    Prev
    Next
    INDEX
    Explanations

    sentences that express various degrees of opinion or sentiment

    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
    0:0.04
    1:0.02
    2:0.14
    3:0.09
    4:0.08
    5:0.13
    6:0.02
    7:0.05
    8:0.04
    9:0.21
    10:0.03
    11:0.10
    Negative Logits
    AME
    -2.35
    assetsadobe
    -2.30
    borg
    -2.29
     Rhodes
    -2.17
    airo
    -2.16
     junior
    -2.10
    odox
    -2.09
    inker
    -2.09
    dding
    -2.08
    stice
    -2.07
    POSITIVE LOGITS
    �
    4.88
    �
    3.82
     �
    3.45
    �
    3.41
     ¯
    3.20
    ¨
    3.09
    �
    2.94
    ️
    2.92
     hinges
    2.88
    ¯
    2.88
    Activations Density 0.219%

    No Known Activations