© 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. 16557
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the ability or potential to do something

    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
    0:0.13
    1:0.12
    2:0.05
    3:0.05
    4:0.09
    5:0.03
    6:0.14
    7:0.13
    8:0.02
    9:0.03
    10:0.09
    11:0.06
    Negative Logits
     WC
    -3.25
     helium
    -2.84
     vaping
    -2.81
     coron
    -2.68
     puff
    -2.66
     Derby
    -2.61
    Draft
    -2.56
     Atkinson
    -2.47
    atche
    -2.43
    KEY
    -2.42
    POSITIVE LOGITS
     forgive
    6.43
     forgiven
    5.97
     forgiveness
    5.62
     forgiving
    5.14
     forg
    4.56
     pard
    3.81
     Manit
    3.76
     unfor
    3.69
     repent
    3.46
     pardon
    3.38
    Activations Density 0.001%

    No Known Activations